The DOI matches its Crossref record; 73 of the 73 references it cites were found in a registry or an index; none of the 27 sources its claims cite is checked for support yet.
The Design and Implementation of XiaoIce, an Empathetic Social Chatbot
Open accessAbstract
This article describes the development of Microsoft XiaoIce, the most popular social chatbot in the world. XiaoIce is uniquely designed as an artifical intelligence companion with an emotional connection to satisfy the human need for communication, affection, and social belonging. We take into account both intelligent quotient and emotional quotient in system design, cast human–machine social chat as decision-making over Markov Decision Processes, and optimize XiaoIce for long-term user engagement, measured in expected Conversation-turns Per Session (CPS). We detail the system architecture and key components, including dialogue manager, core chat, skills, and an empathetic computing module. We show how XiaoIce dynamically recognizes human feelings and states, understands user intent, and responds to user needs throughout long conversations. Since the release in 2014, XiaoIce has communicated with over 660 million active users and succeeded in establishing long-term relationships with many of them. Analysis of large-scale online logs shows that XiaoIce has achieved an average CPS of 23, which is significantly higher than that of other chatbots and even human conversations.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
This paper describes Microsoft XiaoIce, an empathetic social chatbot designed as an AI companion with IQ, EQ, and personality, optimized for long-term user engagement measured by expected Conversation-turns Per Session (CPS). It reports system architecture, dialogue manager, empathetic computing, Core Chat, skills, and large-scale deployment results, including 660 million active users and an average CPS of 23.
Key findings
- XiaoIce was launched in May 2014 and by July 2018 had over 660 million active users, was deployed in five countries on more than 40 platforms, and achieved an average CPS of 23 in its 6th generation; the paper compares this with CPS 9 for human conversations in its user study and CPS 14.6 for the latest Amazon Alexa systems per Khatri et al. [2018].
- The empathetic computing module’s A/B test on Weibo showed no significant CPS change but increased NAU from 0.5 million to 5.1 million in 3 months; it was released in July 2018 and became the most important feature in the 6th generation.
- Core Chat’s hybrid approach improved expected CPS by 0.5 in two weeks over a retrieval-only baseline; incorporating the neural generator and unpaired-data retrieval improved response coverage by 20% and 10%, respectively. Topic Manager improved Core Chat expected CPS by 0.5, and Image Commenting doubled expected CPS across all dialogues containing images.
- The persona-based neural response generator achieved perplexity 25.0 (−8.4% vs. seq2seq) and BLEU 1.9% (+18.8% vs. seq2seq, +11.8% vs. LSTM-MMI) on the TV series dataset; the XiaoIce Image Commenting prototype scored BLEU-4 4.53, ROUGE-L 15.33, CIDEr-D 3.21, METEOR 15.51, and SPICE 4.82, outperforming four state-of-the-art image captioning systems.
Methods
- Design: XiaoIce is a modular system with user experience, conversation engine, and data layers; social chat is cast as hierarchical decision-making over options in Markov Decision Processes, with a dialogue manager, empathetic computing module, Core Chat, and 230 dialogue skills, optimized for expected CPS.
- Data and training: paired conversational data included more than 30 billion conversation pairs as of May 2018, with 70% of XiaoIce’s responses retrieved from her own past conversations; classifiers for user understanding were trained on 10K manually labeled dialogue sessions, the response ranker on 50K manually labeled dialogues, neural generation and ranking features on 50 million human dialogues, and Image Commenting on 28 million images each paired with 6 text comments.
- Evaluation: A/B tests used expected CPS and NAU; pilot studies used human ratings on a 3-level quality scale and benchmark metrics such as perplexity, BLEU, METEOR, CIDEr, ROUGE-L, and SPICE; large-scale online logs were analyzed over long periods.
Limitations
- The paper states that automatic evaluation of open-domain dialogue systems is “by no means a solved problem,” that common automatic metrics have limitations, and that a unified modeling framework for XiaoIce “remains to be proved” effective.
- The paper states that fully grounding all conversations in the physical world for goal-oriented interactions remains a non-trivial challenge, and that the fundamental mechanism of human-level intelligence is not yet fully understood.
- The paper discusses ethical concerns including privacy, who is in control, unrealistic user expectations, and potential misuse; evident from the text, many key results come from proprietary A/B tests and online logs without reported confidence intervals or full statistical details, and the comparison to human conversations relies on an unspecified user study.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
45 No basis given · 41 Own interpretation · 34 Own result · 22 Not checked yet · 20 Own method
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Although the overall quality of the candidates generated from the unpaired database is lower than those retrieved from the paired database, with unpaired database XiaoIce can cover a much broader range of topics.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Although the overall quality of the candidates generated from the unpaired database is lower than those retrieved from the paired database, with unpaired database XiaoIce can cover a much broader range of topics.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption: The unpaired database sentences from public lectures and quotes are suitable as candidate responses for XiaoIce.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The unpaired database we have used in XiaoIce consists of sentences collected from public lectures and quotes in news articles and reports.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The module was released in July 2018, and became the most important feature in the 6th generation of XiaoIce that has substantially strengthened XiaoIce's emotional connections to human users and increased XiaoIce's NAU.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Although we do not observe any significant change in CPS, NAU is increased from 0.5 million to 5.1 million in 3 months.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Although we do not observe any significant change in CPS, NAU is increased from 0.5 million to 5.1 million in 3 months.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our finding is that the majority of the 'desired' users are young, female users.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Nowadays, 70% of XiaoIce's responses are retrieved from her own past conversations.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Although the response candidates retrieved from the paired database is of high quality, the coverage is low because many new or less frequently discussed topics on the Internet forums are not included in the database.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“After the launch of XiaoIce in May 2014, we also started collecting human-machine conversations generated by XiaoIce and her users, which amounted to more than 30 billion conversation pairs as of May 2018.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Probably not a substantial claim. 66
- It may state two separate claims as one. 43
- The quote only partly states this claim. 2
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Over the last 5 years XiaoIce has developed more than 230 skills, ranging from answering questions and recommending movies or restaurants to comforting and storytelling.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The module was released in July 2018, and became the most important feature in the 6th generation of XiaoIce that has substantially strengthened XiaoIce's emotional connections to human users and increased XiaoIce's NAU.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We show how XiaoIce dynamically recognizes human feelings and states, understands user intent, and responds to user needs throughout long conversations.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Despite being extremely knowledgeable due to her access to large amounts of data and knowledge, XiaoIce never comes across as egotistical and only demonstrates her wit and creativity when appropriate.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“As shown in Figure 2, XiaoIce demonstrates sufficient EQ as it generates socially acceptable responses (e.g., having a sense of humor, comforting, etc.), and can determine whether to drive the conversation to a new topic when e.g., the conversation has stalled, or whether or not to be actively listening when the user herself is engaged in the conversation.”
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The most important and sophisticated skill is Core Chat, which can engage long and open-domain conversations with users.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Analysis of large-scale online logs shows that XiaoIce has achieved an average CPS of 23, which is significantly higher than that of other chatbots and even human conversations.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This is possible because XiaoIce has attracted a large number of active users since her launch in 2014.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As shown in Figure 7, while a typical seq2seq model which is not grounded in any persona often outputs inconsistent responses Li et al. [2016b], XiaoIce is able to generate consistent and humorous responses.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As shown in the example in Figure 3, XiaoIce switches to a new but related topic (i.e., a song titled 'the time machine' by Ashin in Turn 13) when she detects that the user is not familiar with 'Ashin' and about to terminate the conversation by responding 'Ah! Boring' and 'Okay, I am going to bed'.”
plaindirectSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Since the release in 2014, XiaoIce has communicated with over 660 million active users and succeeded in establishing long-term relationships with many of them.”
- Also stated in: § 1 Introduction · p. 1 · plain
“Since her launch in China in May 2014, XiaoIce has attracted over 660 million active users (i.e., subscribed users).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
- Also stated in: § 1 Introduction · p. 1 · plain
In the paper
“As shown in Table 1, the persona model significantly outperforms both baselines, achieving a lower perplexity (-8.4%) and a higher BLEU score (+18.8% and +11.8%) Papineni et al. [2002].”
What the sources say
- Not checked yetcites Papineni et al. [2002]
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“XiaoIce has been deployed on many platforms. As a result, we have witnessed the creation and growth of a XiaoIce ecosystem since 2016.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“XiaoIce-generated TV and Radio programs have covered 9 top satellite TV stations, and have attracted over 800 million weekly active audience.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As shown in Figure 5 (a), CQU rewrites user queries to include necessary context, e.g., replacing 'him' in Turn 12 with 'Ashin', 'that' with 'The Time Machine' in Turn 14, and adding 'send The Time Machine' in Turn 15.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Every poem in the album is jointly written by XiaoIce and human poets.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“XiaoIce, however, generates a factual response based on the user's geographical location and the corresponding database, as shown in Figure 19 (a).”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“On May 15, 2018, XiaoIce published the first AI-created Chinese poem album in history 11 .”
What the sources say
- Not checked yetcites [11] Cuayáhuitl Heriberto, 2018
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“XiaoIce is equipped with 230 dialogue skills, which, together with Core Chat and Image Commenting, form the IQ component of XiaoIce.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Since July 2014, XiaoIce has released 230 skills, which amounts to nearly one new skill every week, as shown in Figure 21.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Depending on the availability of training data and knowledge bases for each individual task, either a rule-based method or a data-driven method, or a hybrid of both is adopted for the task.”
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“XiaoIce, on the other hand, is designed as an AI companion which integrates both EQ and IQ skills that are needed to help users complete specific tasks.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Up to August 2015, XiaoIce has had more than 10 billion conversations with humans.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We found that the pairs that are shared among acquaintances (e.g., coworkers, classmates and friends) are of good quality, and amount to a large portion in the database.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“These characters include more than 60,000 official accounts, e.g., Lawson and Tokopedia's customer service bots, Pokemon, Tecent and Netease's chatbots, and even real human celebrities such as the singers of Guoyun Entertainment.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“From 2015 on, XiaoIce started powering third party characters, personal assistants and real human's virtual avatars.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In two months, XiaoIce successfully became a cross-platform social chatbot.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“As of July 2018, XiaoIce has been deployed on more than 40 platforms, and has attracted 660 million active users.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The longest conversation lasts for more than 6 hours, covering 53 different topics across 8 domains and using 16 task-completion skills.”
plainSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The XiaoIce Poetry Generation skill has helped over four million users to generate poems.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“XiaoIce was first launched on May 29, 2014, and went viral immediately.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“By then, users have proactively posted more than 6 million conversation sessions to public.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Within 72 hours, XiaoIce was looped into 1.5 million chat groups.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“The CPS is close to the 3rd generation of XiaoIce, as shown in Figure 20.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Compared to the neural response generator which often generates well-form but short responses, the candidates from unpaired database are much longer with more useful content.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Through a long conversation, XiaoIce has demonstrated human-like empathy and social skills, and eventually helped the user regain her confidence and move forward with a positive attitude.”
boosteddirectSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“| XiaoIce (prototype) | 4.53 | 15.33 | 3.21 | 15.51 | 4.82 |”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one. The quote only partly states this claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“For example, although XiaoIce can provide answers to many questions due to the access to the large scale knowledge graph, these answers are not always accurate.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“XiaoIce cheers users up, encourages them, helps them accomplish tasks, and holds their attention throughout the conversation.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“As an AI companion of human users, XiaoIce can recognize user interests and intents much more accurately than traditional intelligent personal assistants.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“While XiaoIce carefully leverages this information to serve users and build emotional bonds over a long period of time”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“When working on the modules or tasks where there are benchmarks used in the research community, such as the neural response generator (Section 4.3), we often compare our approaches to other state-of-the-art methods using these benchmarks.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Neural-model-based and retrieval-based generators are complementary: the neural-model-based generator offers robustness and high coverage, while the retrieval-based provides high-quality responses for popular topics.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The dialogue policy is designed to optimize long-term user engagement through an iterative, trialand-error process based on the feedback of XiaoIce's users.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
- The authors state this as an assumption: Human-machine social chat can be modeled as a hierarchical decision-making process over Markov Decision Processes.
- The authors state this as an assumption: Expected CPS is a valid measure of long-term user engagement for social chatbots.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“A social chatbot needs to present a consistent personality to set the right expectations for users in the conversation and gain their long-term confidence and trust.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This paper describes the development of Microsoft XiaoIce , the most popular social chatbot in the world.”
- Also stated in: § 1 Introduction · p. 1 · plain
“In this paper we present the design and implementation of Microsoft XiaoIce ('Little Ice' literally in Chinese), the most popular social chatbot in the world.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Also stated in: § 1 Introduction · p. 1 · plain
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Social chatbots require a sufficiently high IQ to acquire a range of skills to keep up with the users and help them complete specific tasks.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Topic Manager simulates human behavior of changing topics during a conversation.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Empathetic computing reflects XiaoIce's EQ and models the empathetic aspects of the humanmachine conversation.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
In the paper
“More importantly, social chatbots also require a sufficient EQ to meet users' emotional needs, such as emotional affection and social belonging, which are among the fundamental needs for human beings Maslow [1943].”
What the sources say
- Not checked yetcites Maslow [1943]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Implementation of the conversation engine relies heavily on A/B test to evaluate if a new module or a new dialogue skill is going to improve an existing component.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In the past, the Turing Test has been used to evaluate chitchat performance. But it is not sufficient to measure the success of long-term, emotional engagement with users.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“To ensure a smooth conversation, we avoid switching among different skills too often. We prefer keeping the running skill activated until it terminates to activating a new skill.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In Figure 3, XiaoIce tries a new topic (i.e., a popular singer named Ashin) in Turn 5 and recommends a song in Turn 15, and thereby learns the user's preferences (e.g., the music topic and the singer he loves), knowledge that would lead to more engagement in the future.”
plaindirectSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“XiaoIce wins the user's trust and friendship by her wonderful sense of humor and empathetic responses to all sorts of questions, some of which are quite challenging, such as “you are all lies”, and “who is your daddy”.”
plaindirectSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Thus, XiaoIce has to interact with the user's environment and access real-world knowledge e.g., via API calls.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: Traditionally, social chatbots are designed for chitchat scenarios where bots are expected to mimic human user conversations but not to interact with the user's environment.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Each generated response is labeled on the 3-level quality scale by three human judges.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
- Rests on an assumption: The 3-level quality scale labels assigned by human judges reliably measure response quality.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In the short term, incorporating many task-completion skills can reduce the CPS since these skills help users accomplish tasks more efficiently by minimizing the CPS.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Through a long conversation, XiaoIce has demonstrated human-like empathy and social skills, and eventually helped the user regain her confidence and move forward with a positive attitude.”
boosteddirectSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“To human users, it is these latter aspects that are more important to drive a meaningful and interesting conversation.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Compared with traditional personal assistants, XiaoIce's task-completion skills offer more perspectives and empathy in generating interpersonal responses.”
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“According to Khatri et al. [2018], the latest Alexa systems have achieved the CPS of 14.6, an increase of 54% since the launch of the 2018 competition.”
What the sources say
- Not checked yetcites Khatri et al. [2018]
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“To control the data quality, a pipeline similar to that for Core Chat is applied to retain only the pairs whose text comments fit XiaoIce's persona 9 .”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It can be observed that the XiaoIce-produced comments are emotional, subjective, imaginative, and are very likely to inspire meaningful human-machine interactions, while the comments generated by the other image captioning models are reasonable in content but boring in the context of social chats, and thus less likely to improve user engagement.”
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The response candidate ranker is trained using 50K manually labeled dialogues.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The use of neural response generator in Core Chat, starting from the 5th generation, significantly improves the coverage and diversity of XiaoIce's responses.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The full duplex voice mode released in the 5th generation has made the humanmachine communication substantially more natural, thus significantly increasing the length of conversation sessions.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is the latter, the social skill aspects, that distinguishe image commenting from other traditional vision tasks such as image tagging and image description, as illustrated in Figure 11.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As a result, it helps drive the number of active users from 500 million to 660 million, and keep the CPS to 23 in spite of the incorporation of many task-completion tasks that are designed to minimize the CPS such as those that control the smart devices.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“But in the long run, these new skills not only help grow XiaoIce's NAU by meeting user needs and strengthening the emotional bond with human users, but also provide large amounts of training data to improve the core conversation engine e.g., by optimizing the neural response generation models, empathy models, and the dialogue manager, etc.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
In the paper
“The second is the LSTM-MMI model Li et al. [2016a], which is one of the state-of-the-art neural response generation models.”
What the sources say
- Not checked yetcites Li et al. [2016a]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Therefore, low BLEU (or other metrics) scores do not necessarily indicate low quality as the number of reference responses is always limited in the test set.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one. The quote only partly states this claim.
- Rests on an assumption: In open-domain dialog systems, the same input may have many plausible responses that differ in topics or contents significantly.
- Rests on an assumption: The number of reference responses in the test set is always limited.
In the paper
“Galley et al. [2015] showed that the correlation of string-based metrics (e.g., BLEU and deltaBLEU) significantly increases with the units of measurement bigger than a sentence.”
What the sources say
- Not checked yetcites Galley et al. [2015]
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“But as pointed out in Gao et al. [2019], the correlation analysis by Liu et al. [2016] is performed at the sentence level while BLEU is designed from the outset to be used as a corpus-level metric.”
What the sources say
- Not checked yetcites Gao et al. [2019]
- Not checked yetcites Liu et al. [2016]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Retrieval-based methods are often evaluated using traditional information retrieval metrics Manning et al. [2008] such as as Precision@K, Mean Average Precision (MAP), and normalized Discounted Cumulative Gain (nDCG).”
What the sources say
- Not checked yetcites Manning et al. [2008]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, even a completely deterministic function can lead to unpredictable behavior. For example, a simple answer 'Yes' by XiaoIce could be perceived offensive in a given context.”
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is not surprising, then, that with vastly more people being digitally connected in the social media age, social chatbots have become an important alternative means for engagement.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
- Rests on an assumption: Happiness and meaningful conversations often go hand in hand.
None of the sources cited for this claim have been checked yet.
In the paper
“Generation-based methods are evaluated using those metrics borrowed from text generation tasks like machine translation and text summarization, using string and n-gram matching metrics such as BLEU Papineni et al. [2002], METEOR Banerjee and Lavie [2005] and ROUGE Lin [2004].”
What the sources say
- Not checked yetcites Papineni et al. [2002]
- Not checked yetcites Banerjee and Lavie [2005]
- Not checked yetcites Lin [2004]
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This could mislead the XiaoIce users by setting an unrealistic expectation. As a result, the users might become addicted after chatting with XiaoIce for a very long time.”
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“While manual evaluation is reliable, it is very expensive and chatbot developers often have to resort to automatic metrics for quantifying day-to-day progress and for performing automatic system optimization.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“a score that is substantially better than that of other chatbots and even human conversations”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Commonly used automatic evaluation metrics for open-domain dialogue systems existing today all have their own limitations.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Despite the success of XiaoIce, the fundamental mechanism of human-level intelligence, as demonstrated in human conversations, is not yet fully understood.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“However, as argued by Gao et al. [2019], machine-learned metrics lead to potential problems such as overfitting and 'gaming of the metric' Albrecht and Hwa [2007].”
What the sources say
- Not checked yetcites Gao et al. [2019]
- Not checked yetcites Albrecht and Hwa [2007]
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“deltaBLEU Galley et al. [2015] is an extension to BLEU that exploits numerical ratings associated with conversational responses.”
What the sources say
- Not checked yetcites Galley et al. [2015]
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The databases used by the retrieval-based candidate generators and for training the neural response generator have been carefully cleaned, and a hand-crafted editorial response is used to avoid any improper or offensive responses.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Most open-domain dialogue systems, such as XiaoIce, generate responses using either retrieval-based methods or generation-based methods, or hybrid methods.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Unlike early chatbots designed for chitchat, XiaoIce is designed as a social chatbot intended to serve users' needs for communication, affection, and social belonging, and is endowed with empathy, personality and skills, integrating both EQ and IQ to optimize for long-term user engagement, measured in expected CPS.”
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“As we have shown in Core Chat and Image Commenting, XiaoIce always preserves the right of not discussing or commenting on inappropriate topics and contents.”
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The authors state this as an assumption.
Human-machine social chat can be modeled as a hierarchical decision-making process over Markov Decision Processes.
“we mathematically cast human-machine social chat as a hierarchical decision-making process, and optimize XiaoIce for long-term user engagement, measured in expected CPS.”
“cast human-machine social chat as decision-making over Markov Decision Processes (MDPs)”
The authors state this as an assumption.
Expected CPS is a valid measure of long-term user engagement for social chatbots.
“we propose to use expected Conversation-turns Per Session (CPS) as the success metric for social chatbots.”
“The larger the CPS is, the better engaged the social chatbot is.”
The paper relies on this without support.
An AI companion can satisfy the human need for communication, affection, and social belonging.
“XiaoIce is uniquely designed as an AI companion with an emotional connection to satisfy the human need for communication, affection, and social belonging.”
The paper relies on this without support.
The machine learning classifiers used for user understanding accurately detect user intents, emotions, topics, opinions, and persona from dialogue.
“These key-value pairs are generated using a set of machine learning classifiers as follows.”
The paper relies on this without support.
The TV series dataset used in the first pilot study is representative enough to validate the persona-based neural response generator for XiaoIce.
“In the first pilot study reported in Li et al. [2016b], we compare the persona model against two baseline models, using the TV series dataset for model training and evaluation.”
The paper relies on this without support.
The 3-level quality scale labels assigned by human judges reliably measure response quality.
“Each generated response is labeled on the 3-level quality scale by three human judges.”
The paper relies on this without support.
The KG triples that co-occur often in the same conversations represent related topics humans often discuss.
“We include in the XiaoIce KG a Satori triple ( h, r, t ) only if h and t co-occur often enough in the same conversations. Such a triple contains a pair of related topics ( h, t ) that humans often discuss in one conversation”
The paper relies on this without support.
The unpaired database sentences from public lectures and quotes are suitable as candidate responses for XiaoIce.
“The unpaired database we have used in XiaoIce consists of sentences collected from public lectures and quotes in news articles and reports. These sentences are considered candidate responses R .”
The paper relies on this without support.
Any individual dialogue skill is unlikely to have a significant impact on CPS.
“Since any individual skill is unlikely to have a significant impact on CPS, we measure the user satisfaction of a skill by monitoring its active users and skill triggering rate (i.e., the number of times a skill is activated by users within a day or a week).”
The paper relies on this without support.
Traditionally, social chatbots are designed for chitchat scenarios where bots are expected to mimic human user conversations but not to interact with the user's environment.
“Traditionally, social chatbots are designed for chitchat scenarios where the bots are expected to mimic human user conversations but not to interact with the user's environment.”
The paper relies on this without support.
Happiness and meaningful conversations often go hand in hand.
“Psychological studies show that happiness and meaningful conversations often go hand in hand.”
The paper relies on this without support.
The long-term success of a social chatbot needs to be measured by its user engagement.
“the long-term success of a social chatbot needs to be measured by its user engagement”
The paper relies on this without support.
The most reliable evaluation is to deploy the chatbot to users and monitor user feedback and engagement over a long period.
“There is no doubt that the most reliable evaluation is to deploy the chatbot to users and monitor the user feedback and engagement, measured by user ratings, NAU, CPS, and so on, over a long period of time.”
The paper relies on this without support.
In open-domain dialog systems, the same input may have many plausible responses that differ in topics or contents significantly.
“Nevertheless, in open-domain dialog systems, the same input may have many plausible responses that differ in topics or contents significantly.”
The paper relies on this without support.
The number of reference responses in the test set is always limited.
“as the number of reference responses is always limited in the test set”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Popular social chatbots have millions of users (Zhou et al., 2020), and their user bases are expanding.”
From A longitudinal study of human–chatbot relationships (2022) · cites this paper as Zhou et al., 2020
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 4.3 Core Chat · p. 16
“Our evaluation data consists of 4K dialogue sessions.”
§ 4.3 Core Chat · p. 16
“Table 3: Ratings of three response generation systems on a 5K dialogue dataset.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 4.4 Image Commenting · p. 17
“The generation-based approach uses an image-to-text generator”
§ 4.4 Image Commenting · p. 18
“The components of Image Commenting, including the text-to-image generator and boosted tree ranker, are trained on a dataset consisting of 28 million images”
Citations
Cites
Maslow, A. H. (1943) · Psychological Review · doi:10.1037/h0054346 · Cited by 21,563
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Introduction to information retrieval
(2009) · Choice Reviews Online · doi:10.5860/choice.46-2715 · Cited by 12,278
Axford, N. (2017) · Routledge eBooks · doi:10.4324/9781315258324-16 · Cited by 11,329
Introduction to Information Retrieval
Manning, C. D., Raghavan, P., & Schütze, H. (2008) · doi:10.1017/cbo9780511809071 · Cited by 11,288
(2004) · Cited by 9,718
Picard, R. W. (1997) · MIT Press · doi:10.7551/mitpress/1140.001.0001 · Cited by 7,382
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches
Cho, K., van Merriënboer, B., Bahdanau, D., & Bengio, Y. (2014) · SSST@EMNLP · doi:10.3115/v1/w14-4012 · Cited by 7,251
Show and tell: A neural image caption generator
Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298935 · Cited by 6,318
Research works printed but not linked: 23
- Albrecht Joshua, 2007, Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, 880
- Asimov I., 1984, “The Bicentennial Man” in I. Asimov, The Bicentennial Man and Other Stories
- Banerjee Satanjeev, 2005, Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, 65
- Brahnam Sheryl, 2005, Abuse: The Darker Side of Human Computer Interaction, 62
- Cuayáhuitl Heriberto, 2018, NeurIPS Workshop on Conversational AI
- Dinan Emily, 2018, CoRR
- Fang Hao, 2017, Alexa Prize Proceedings
- Fung Pascale, 2016, CoRR
- Gan Chuang, 2017, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 3137
- Ghazvininejad Marjan, 2018, Proceedings of AAAI, 5111
- Lin Chin-Yew, 2004, Proceedings of the ACL workshop, 74
- Mathews Alexander Patrick, 2016, AAAI, 3574
- Misu Teruhisa, 2012, Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 84
- Mostafazadeh Nasrin, 2017, Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 462
- Papineni Kishore, 2002, Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, 311
- Sai Ananya, 2019, Proceedings of AAAI 2019, 33, 7281
- Serban Iulian Vlad, 2016, AAAI, 16, 3776
- Serban Iulian Vlad, 2017, AAAI, 3295
- Shum Heung-Yeung, 2018, CoRR
- Sutskever Ilya, 2014, NIPS, 3104
- Vinyals Oriol, 2015, ICML Deep Learning Workshop
- Wu Bowen, 2016, Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, 652
- Xing Chen, 2017, AAAI, 17, 3351
Cited by
Sorted by citations
Items 701–800 of 815
Human-AI relationships and their therapeutic implications
O’Driscoll, C., Moltrecht, B., & Dechant, M. (2026) · Mental Health and Digital Technologies · doi:10.1108/mhdt-10-2025-0069
Synthetic Empathy and the Influence Trap
Katoch, H., & Sandhu, D. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-3658-9.ch004
The Frontiers of Technology and Design Using Smarter HCI
Ghosh, S. (2025) · IGI Global eBooks · doi:10.4018/979-8-3373-1444-0.ch004
Inferring Speaking Styles for Conversational Speech Synthesis by Learning Contextual Dependencies
Li, J., Wu, W., Yi, M., Zhang, L., Tian, Q., Wang, Y., Wang, Y., Wu, X., Wu, Z., & Meng, H. M. L. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3589870
Phadnis, N., Gadge, J., & Shah, D. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5751-3_35
Zenimoto, Y., Komata, S., Hasegawa, R., & Utsuro, T. (2025) · Transactions of the Japanese Society for Artificial Intelligence · doi:10.1527/tjsai.40-5_mo25-d
Li, Y., & Liu, Y. (2025) · Research Square · doi:10.21203/rs.3.rs-7437820/v1
Jiang, S., Xu, J., Luo, J., & Pan, Y. (2026) · Humanities and Social Sciences Communications · doi:10.1057/s41599-026-08949-4
It's her! Investigating relationship development with social AI chatbots.Preprint
Rupprechter, N., & Dienlin, T. (2025) · doi:10.31235/osf.io/guc4x_v1
Vivekananthan, J., Sattar, M. U., & Lackner, M. K. (2025) · Journal of Intelligent Systems · doi:10.1515/jisys-2024-0377
How does turning to AI for companionship predict loneliness and vice versa?Preprint
Folk, D. P., & Dunn, E. W. (2025) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/bq7v3_v3
Beyond Full Automation: A Critical Survey of RPA and Human-in-the-Loop Hybrid Workflows
(2025) · International Research Journal of Modernization in Engineering Technology and Science · doi:10.56726/irjmets81047
Chatbots integrated in the metaverse: a conceptual model based on interaction ritual chain theory
Yan, Y., & Fan, M. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3235
Miskell, C., Slhoub, K., & Mensi, N. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-07992-3_17
PT-PT Synthetic Speech Detection
dos Santos, R. G., Sousa, J., & de Oliveira, J. V. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-10486-1_13
AI-Mediated Communication and Digital Dependency
Govindaraj, M., Lawrence, J., N.A., J. P. S., & Anand, N. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-5606-8.ch003
Tiwari, R. A., & Bhura, S. A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5745685
Chatrion:Safer Connection for Smarter Generation
Solanki, J., Koradiya, K., Solanki, N., Oad, V., & Soni, D. S. (2025) · INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · doi:10.55041/ijsrem53775
Les sociabilités privées et les pratiques numériques
Martin, O., & Dagiral, É. (2025) · Réseaux · doi:10.3917/res.253.0013
MemoryBERT: A Systematic Framework for Memory Identification
Panagoulias, D. P., Papatheodosiou, P., Bonakis, A., Dikeos, D. G., Virvou, M. K., & Tsihrintzis, G. A. (2025) · IEEE International Conference on Bioinformatics and Bioengineering (BIBE) · doi:10.1109/bibe66822.2025.00123
“Can You Be My Mom?” Exploring Human Interactions with Role-Based ChatbotsPreprint
Zhang, Y., Liu, C., & Seo, M. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5928850
CUTTING EDGE INNOVATIONS IN ARTIFICIAL INTELLIGENCE POWERED CHATBOT TECHNOLOGY
Varghese, R. K. (2025) · International Journal of Novel Research and Development · doi:10.56975/ijnrd.v10i12.311222
Chen, I., & Lu, J. (2026) · International Journal For Multidisciplinary Research · doi:10.36948/ijfmr.2026.v08i01.60765
Integrating Behavioural Science using the Psycho-Intelligence Framework in Connected Systems
Iwendi, C., Nwibo, E. G., Sharma, V., Lemeke, C., Uwah, S. E., & Ukura, K. K. (2025) · IEEE International Conference on ICT in Business Industry & Government (ICTBIG) · doi:10.1109/ictbig68706.2025.11323725
The Trust Paradox: How Companion AI Is Rewiring Human Connection and Social Cohesion
Markelius, A., Chaves, P., Spencer, S., & Kuiper, J. (2025) · The Paris Journal on AI & Digital Ethics · doi:10.65701/c6k1x9r3n0
Enhancing Public Service Delivery Through Empathetic, Intelligent Arabic Chatbots
Bekki, K., Rouabhi, M., Bouamrane, K., & Ouared, A. (2025) · International Conference on Intelligent Computer Systems, Data Science and Applications (IC2SDA) · doi:10.1109/ic2sda68097.2025.11331460
Chen, W., Wang, Y., & Zhou, T. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6128326
Gao, R., Wen, X., Liu, G., Huo, H., & Fang, T. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343313
Liu, X., & Lee, K. C. (2025) · International Journal of Modern Education · doi:10.35631/ijmoe.728015
Why should I use social chatbots? On potential users’ acceptance and the role of anthropomorphism
Rüth, M., Eifler, J., & Schneider, A. C. (2026) · Frontiers in Psychology · doi:10.3389/fpsyg.2026.1656749
Talebian, S. H., Ibrahim, A. O., & Syed, H. J. (2025) · International Conference on Advances in Machine Intelligence and Cybersecurity Technologies (AMICT) · doi:10.1109/amict65811.2025.11402818 · Cited by 1
Proposal of an Emotion Estimation Method for Speech Using Knowledge Distillation
Hamaguchi, O., & Morita, K. (2025) · IEEE Region Humanitarian Technology Conference · doi:10.1109/r10-htc63995.2025.11394012
Ying, L. Y. (2026) · Psi Chi Journal of Psychological Research · doi:10.24839/2325-7342.jn2026.004
Yu, J. (2025) · International Association of Societies of Design Research Congress (IASDR) · doi:10.21606/iasdr.2025.272
An Adaptive AI Tool for Introductory French and German Courses
Dwivedi, S., Deshpande, A., Gopalan, K., & Bhuskute, A. (2026) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-95-4423-3_17
User Acceptance of Social Chatbots in Emotional Companionship Services: An AIDUA-Based Perspective
Li, W., Ye, X., He, X., & Zhou, Y. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2645438
The Impact of Artificial Empathy in Using ChatGPT on User's Feeling Heard
Angelica, K., Andangsari, E. W., & Chowanda, A. (2026) · International Conference on Cognitive Systems and Computer Interaction (ICoSCI) · doi:10.1109/icosci66700.2026.11447712
Human Skill Development in the Age of AI Personhood
Morancho, M. V., & Posca, M. (2026) · Oxford University Press eBooks · doi:10.1093/9780198945215.003.0171
AI-Powered Petition Chatbot for Smart Grievance Management and Urgency Analysis
Parameswari, M., Mohanraj, V., Jayasuriya, B., Jeeva Mary, S., Keerthana, G., & Yuvaprasanth, L. (2026) · International Conference on Communication, Computing and Electronics Systems (ICCCES) · doi:10.1109/iccces62661.2026.11436618
Analysis and control of online interactions through neural natural language processing
Laugier, L. (2022) · theses.fr (ABES) · doi:10.70675/4743aa15z209az4addz8f29z95150aa230b8
AI of Oz: Enhancing Wizard of Oz Studies in HCI with AI Assistance for Human Moderation
Wen, R., Gupta, K., Nanthakumar, K., Han, B., Hoermann, S., Billinghurst, M., Nassani, A., Allan, D. D., & Piumsomboon, T. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791324
RECALLbot: Designing Agentic Memory and Reciprocal Disclosure for Human–Chatbot Relationships
Jiang, Z., Zheng, C., Chen, H., & Chen, L. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790714 · Cited by 7
Progga, F. T., & Rubya, S. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791664
Lv, S., Xu, W., Hu, R., Hu, R., Wu, Y., Du, F., Du, X., Yin, J., Guo, T., Li, S., et al. (2026) · doi:10.2196/preprints.97868
SURE: Synergistic Uncertainty-Aware Reasoning for Multimodal Emotion Recognition in Conversations
Cai, Y., Wu, C., Ma, B., Chen, B., Xue, Y., Hirschberg, J., & Gong, Z. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464547
Zhang, W., Jin, H., Wang, S., Wei, Z., & Dang, T. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464198
Dialogue Systems Through the Decades: A Survey of Taxonomies and Shifting Paradigms
Shah, J., & Thakkar, P. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-19675-0_38
People Keep Caring for Flawed AI in PracticePreprint
Zhang, H., Luokuan, Z., Li, Q., Ye, T., Yi, L., Danil, K., & huang, L. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6613720
From Function to Feeling: An Emotion-centered Framework for Inclusive Participatory Design
Wang, Y. (2025) · International Conference on Human-Engaged Computing (ICHEC) · doi:10.1145/3786995.3787003
Crazy Close to the Real Thing: Questioning the Value of AI Companions
Hasselberger, W., & Lott, M. (2026) · Springer eBooks · doi:10.1007/978-3-032-15112-4_43
Weinreich, L., von Kontz, L.-M., Witzel, B., Hermansson, O., Hampe, H. L., Volkmer, S., Schulte‐Körne, G., & Moll, K. (2026) · Journal of Medical Internet Research · doi:10.2196/64903
Chen, A., Hu, S., & Wang, X. (2026) · Industrial Management & Data Systems · doi:10.1108/imds-03-2025-0332
Neuroscience of Emotional Intelligence: An Integrative Narrative Review
Ali, A., Kulo, V., Al-Rumaihi, G., Sethi, A., Elnashar, M. S., Shaikh, N., & Jahangiri, F. R. (2026) · Cureus · doi:10.7759/cureus.108949
Generative AI Companions and the Cognitive and Affective Incorporation of the Ersatz Other
Clowes, R. W. (2026) · Synthese Library/Synthese library · doi:10.1007/978-3-032-10073-3_3 · Cited by 1
Emotional Intelligence: A Human-Centred AI Perspective
Gámez, M. E. (2026) · Springer eBooks · doi:10.1007/978-981-95-3658-0_109
Generalized psychology and human wellness in the era of artificial intelligence: A review
Jia, S., Ren, Y., Wu, M. S., & Peng, K. (2026) · Well-Being Sciences Review · doi:10.54844/wsr.2025.1113
Alam, N. (2026) · Journal of Couple & Relationship Therapy · doi:10.1080/15332691.2026.2670271
Only Time Will Tell: A Structured Survey of Longitudinal Studies on Social AI Companions
Pi, Y., & Hunter, R. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2670529
Tatu, C. I., Chivu, R.-G. P., Orzan, M., Moise, D., & Boboc, L. (2026) · Journal of Intelligence · doi:10.3390/jintelligence14060098 · Cited by 1
Sun, Y., Liu, J., Liu, T., Wei, Z., & Shen, H. (2026) · Frontiers in Psychology · doi:10.3389/fpsyg.2026.1855345
Fast-Food Intimacy: How Chinese Women Navigate Soul's AI Boyfriend
Lai, H., & Cheon, E. (2026) · Designing Interactive Systems Conference · doi:10.1145/3800645.3812992
Elfleet, M., O’Hagan, J., Khamis, M., & Chollet, M. (2026) · Designing Interactive Systems Conference · doi:10.1145/3800645.3812948 · Cited by 2
Not Too Early, Not All at Once: Design Tensions in AI-Mediated Self-Disclosure in Online Dating
Tsai, P.-H., Zhang, T., Poh, E., Tang, A., & Chang, Y.-J. (2026) · Designing Interactive Systems Conference · doi:10.1145/3800645.3812961
Personality-driven trust and satisfaction in AI chatbots: a behavioral economics perspective
Klunklin, P., Tantiprabha, P., Maneesong, O., Changchit, C., & Lonkani, R. (2026) · Review of Behavioral Economics · doi:10.1108/rbe-09-2025-0089
Semantic context improvisational retrieval-augmented generation for empathic conversational AI
Tahir, S. A., Johnson, J., Abu-Khalaf, J., & Shah, S. A. A. (2026) · Neural Computing and Applications · doi:10.1007/s00521-026-12167-z
Dhoble, A. K., Bandekar, R., & Ingole, M. (2026) · International Journal of Drug Delivery Technology · doi:10.25258/ijddt.16.59s.157
Katz, J. E. (2026) · Frontiers in Communication · doi:10.3389/fcomm.2026.1895848
Zengzhan, X., & mingpeng, L. (2026) · Computers in Human Behavior · doi:10.1016/j.chb.2026.109111
Cognitive AI Agents and Natural Language Processing Transforming Higher Education
Farooqi, A. H. A. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-2811-7.ch003
Insights of higher-level educators on integrating AI technology into their teaching practices
Ali, D. (2026) · Caribbean Educational Research Journal · doi:10.1108/cerj-04-2026-0010
Stakeholder-Informed Design of LLM-Based Chatbots for Post-secondary Mental Health Support
Shayaninasab, M., Kim, J. E., Kitson, A., & Yalçın, Ö. N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31048-4_8
‘She lifted me up’: kinship construction in human-AI resilient communication among Chinese users
Li, Y. W., Luo, M., & Ren, H. (2026) · Frontiers in Psychology · doi:10.3389/fpsyg.2026.1832594
Wang, Y., & Wang, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29903-1_30
A Comparative Pragmatic Analysis of AI-Generated and Human Apologies in Iraqi EFL Learners
Mohammed, S. H., & Turki, H. Y. (2026) · Arab World English Journal · doi:10.24093/awej/call12.11
Li, S., Huang, K., Huang, H., & Xuan, C. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2699362
Human Reactions to Artificial Intelligence with Anthropomorphic Features
(2026) · Frontiers research topics · doi:10.3389/978-2-8325-8329-6
Li, S., Liang, K.-H., Shahriar, S., Ye, Y., Goetsu, S., Du, W., Yoshida, M., Ohwa, T., Xu, X., & Yu, Z. (2026) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3816046.3816277
The Impact of Chatbots on Organizations
Lopes, I., Guarda, T., Fernandes, A., & Ribeiro, M. I. (2026) · Springer proceedings in business and economics · doi:10.1007/978-3-032-24600-4_31
de Quijada, P. E. S., Landaeta, C. L. R., Landaeta, B. C. R., Caicedo, L. A., & Figueroa, E. J. A. (2026) · South American Sciences · doi:10.63330/sasciencesv6n2-107
ExpressionCueLens: a cross-cultural analysis of human-AI companion conversations on social media
Ng, L. H. X., Xiao, Y., WANG, L. Z., Xuan, W., & Diab, M. (2026) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-026-05109-z
Um, B., & Ayobi, A. (2026) · Research Square · doi:10.21203/rs.3.rs-9839856/v1
Persuasive Artificial Intelligence and Emotional Attachment to AI
Toplu, S. (2026) · Springer eBooks · doi:10.1007/978-3-031-52643-5_265-1
The Future Trajectories of AI-Mediated Reconfiguration of Global Media Industries
Vukanović, Z. (2026) · Springer eBooks · doi:10.1007/978-3-032-28082-4_34
Disruptive Horizons: Emerging AI Technologies Poised to Reshape the Global Media Industry
Vukanović, Z. (2026) · Springer eBooks · doi:10.1007/978-3-032-28082-4_29
Liu, D., Pan, L., Sabri, A. Q. M., & Fan, G. F. (2026) · ACM Transactions on Social Computing · doi:10.1145/3844666
Chen, X., Ding, S., Hou, S., & Chai, C. (2025) · International Symposium on Computational Intelligence and Design · doi:10.1109/iscid68789.2025.00026
礒部, わ., Shimada, H., & 20467195 (2026) · Institutional Repositories DataBase (IRDB)
Perry, A., & Cameron, C. D. (2026) · Cambridge University Press eBooks · doi:10.1017/9781009639057.002
Models Match or Surpass Objective Human Performance on Various Tasks
Goldstein, A., & Stanovsky, G. (2026) · Cambridge University Press eBooks · doi:10.1017/9781009639057.006
Baltezarević, R., Wei, L.-W., Izgarević, D., & Azdejković, M. (2026) · International Journal of Cognitive Research in Science Engineering and Education · doi:10.23947/2334-8496-2026-14-2-373-384
(2023) · Universidad Pontificia Comillas eBooks · doi:10.14422/9788484686057
La revolución de la inteligencia artificial
Lumbreras, S., & Rayón, A. (2023) · Universidad Pontificia Comillas eBooks · doi:10.14422/9788484686057-02
Dijital Danışmanlık ve Yeni İletişim Arkadaşı Olarak Yapay Zeka
Tutal, B. T. (2026) · Özgür Yayınları eBooks · doi:10.58830/ozgur.pub1418.c5719
Güven, D. (2026) · Özgür Yayınları eBooks · doi:10.58830/ozgur.pub1418.c5721
Sanal Kaytarma: Açık Sekmede Dinlenmek, Yeni Çağın Kaçış Halleri
TERZİ, A. Ö. (2026) · Özgür Yayınları eBooks · doi:10.58830/ozgur.pub1418.c5713
Aboshi, S., Thomas, D., & Moshfeghi, Y. (2026) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2026.103941
Piispanen, J.-R., Myllyviita, T., Vakkuri, V., & Rousi, R. A. (2026) · Information and Software Technology · doi:10.1016/j.infsof.2026.108340
Metadata
- Authors
- Zhou, L., Gao, J., Li, D., & Shum, H.-Y.
- Affiliations
- Microsoft (United States) (US)
- Venue
- Computational Linguistics
- Publisher
- MIT Press
- Published
- 2020-03
- Volume
- 46
- Issue
- 1
- Pages
- 53-93
- ISSN
- 0891-2017 (ISSN-L)
- 1530-9312
- OpenAlex
- W2906579211
- Semantic Scholar
- 66b7d31527f980bb2eecc23629f08ba6037facc4
- Cited by
- 777
- References
- 66
- Citations by year
- 2026: 97 · 2025: 109 · 2024: 106 · 2023: 113 · 2022: 120 · 2021: 112 · 2020: 94
- FWCI
- 43.11
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- cc-by-nc-nd
- Locations
- Computational Linguistics (publishedVersion, cc-by-nc-nd)
- arXiv (Cornell University) (submittedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Funders
- Microsoft Research
- Microsoft Research Asia
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Social Sciences › Business, Management and Accounting › Marketing › AI in Service Interactions
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Keywords
- social chatbots, Markov decision process, dialogue management, user engagement, emotion recognition, user intent understanding
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-08, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-08 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
