Survey of Hallucination in Natural Language Generation
Open accessThe DOI matches its Crossref record; 355 of the 360 references it cites were found in a registry or an index, and 4 are not checked yet; 224 of the 256 sources its claims cite were checked for support.
Abstract
Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation, and data-to-text generation. However, it is also apparent that deep learning based generation is prone to hallucinate unintended text, which degrades the system performance and fails to meet user expectations in many real-world scenarios. To address this issue, many studies have been presented in measuring and mitigating hallucinated texts, but these have never been reviewed in a comprehensive manner before. In this survey, we thus provide a broad overview of the research progress and challenges in the hallucination problem in NLG. The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions, and (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, and machine translation. This survey serves to facilitate collaborative efforts among researchers in tackling the challenge of hallucinated texts in NLG.
Verified 2026-11-19 · 4 references not checked yet
Overview
CoChat Summary
TL;DR
This survey provides a broad overview of hallucination in natural language generation, covering definitions, contributors, metrics, mitigation methods, and task-specific progress across summarization, dialogue, GQA, data-to-text, machine translation, vision-language generation, and LLMs. It distinguishes intrinsic from extrinsic hallucination and argues that hallucination must be treated differently across tasks and sources.
Key findings
- The survey categorizes hallucination into intrinsic hallucination, where generated output contradicts the source, and extrinsic hallucination, where output cannot be verified from the source; extrinsic hallucination is not always erroneous because it may come from factually correct external information.
- It reports prevalence examples from cited work: 25% of summaries generated by state-of-the-art abstractive summarization systems have hallucinated content; 62% of first sentences in WIKIBIO have additional information not stated in the corresponding infobox; and 74% of samples in the QMSum dataset consist of inconsistent facts.
- It reviews hallucination metrics as statistical, model-based (IE-based, QA-based, NLI-based, faithfulness classification, LM-based), and human evaluation, and mitigation methods as data-related and modeling/inference methods including architecture changes, planning/sketching, RL, multi-task learning, controllable generation, and post-processing.
- For LLMs, it notes that RLHF reduced the hallucination rate from 41% to 21% in closed-domain tasks for InstructGPT, and discusses reference-dependent and reference-free hallucination metrics plus mitigation via data refinement, RAG, safety fine-tuning, model editing, decoding methods, chain-of-thought variants, post-processing, and ensembling.
Methods
- Literature survey design: the paper reviews existing research on hallucination in NLG rather than conducting new experiments or primary data collection.
- Coverage: general NLG hallucination topics (definitions, contributors, metrics, mitigation, future directions) plus task-specific sections on abstractive summarization, dialogue generation, generative question answering, data-to-text generation, neural machine translation, vision-language generation, and large language models.
- Analysis: synthesizes and compares definitions, metrics, mitigation approaches, and future directions across tasks, with examples in tables and figures; the LLM section was updated in Jan 2024.
Limitations
- The paper states that GQA has no standard definition or categorization of hallucination and no automatic metric specifically for hallucination in GQA; it also notes that open-domain dialogue lacks a standard hallucination metric and that VL hallucination research is still in its early stage.
- The paper states that extrinsic hallucination has been somewhat overlooked and is more challenging to reduce, and that most existing mitigation methods do not distinguish between intrinsic and extrinsic hallucination.
- Evident from the text: as a survey, it does not provide new empirical validation of metrics or mitigation methods, and its LLM coverage is explicitly updated only through Jan 2024, so later work is not included.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
124 Valid · 26 Not valid · 19 Not checked · 135 Own results and interpretations
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“Furthermore, perturbation, where the insertions of most common tokens are placed at the beginning of the sentence, seems to be the most successful in hallucination mitigation.”
What the sources say
- Not checked — no full text of the sourcecites [133] [133] Katherine Lee, Orhan Firat, Ashish Agarwal, Clara Fannjiang, and David Sussillo. 2019. Hallucinations in Neural Machine Translation. ICLR (2019). -
- Disputedcites [215] [215] Vikas Raunak, Arul Menezes, and Marcin Junczys-Dowmunt. 2021. The Curious Case of Hallucinations in Neural Machine Translation. (4 2021), 1172-1183. https://arxiv.org/abs/2104.06683v1 - sourceExperimental — accuracy not yet measured
In the passage describing the perturbation procedure (page unavailable), the paper says that inserting common tokens at the beginning is used to generate hallucinations, not mitigate them. Its prevention section instead discusses approaches such as robust learning and corpus-level filtering. (LLM, conf=0.92)
Checked by a reasoning model — may be wrong.
hedgedstates a cause- 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.
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“While there are works on the visual extension of faithfulness-oriented RLHF [303], these essentially involve labeling more data, which is expensive and difficult to scale.”
What the sources say
- Disputedcites [303] [303] Tianyu Yu, Yuan Yao, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, and Tat-Seng Chua. 2023. RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback. CoRR abs/2312.00849 (2023). https://doi.org/10.48550/ARXIV.2312.00849 arXiv:2312.00849 - sourceExperimental — accuracy not yet measured
RLHF-V does use human annotation for visual-model alignment, but it makes the contrary point about needing more labeled data. The Fine-grained Correctional Human Preference Collection section says its corrections improve data efficiency, and Section 4.3 reports comparable hallucination rates using only 200 preference examples versus an order of magnitude more ranking-labeled examples. Our copy does not establish a separate claim about annotation cost or scalability. (LLM, conf=0.88)
Checked by a reasoning model — may be wrong.
plainstates a cause- 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.
- Disputed
Every source the paper cites for this claim was checked and supports it.
In the paper
“Nevertheless, as illustrated by Falke et al. [66], off-the-shelf NLI models tend to transfer poorly to the abstractive summarization task.”
What the sources say
- Supportedcites [66] [66] Tobias Falke, Leonardo FR Ribeiro, Prasetya Ajie Utama, Ido Dagan, and Iryna Gurevych. 2019. Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics . 2214-2220. - source
The Introduction states that models trained on NLI datasets transfer poorly to the paper’s downstream task of ranking generated summaries by correctness. The Conclusions likewise say that out-of-the-box NLI models do not perform well on that task. (LLM, conf=0.94)
- 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.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Such wrong association results in generation with facts mixed up between two similar entities [60, 233].”
What the sources say
- Partly supportedcites [60] [60] Nouha Dziri, Andrea Madotto, Osmar Zaiane, and Avishek Joey Bose. 2021. Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding. EMNLP (2021). - sourceExperimental — accuracy not yet measured
The GPT2-KG passage describes an incorrect association between entities, and G Error Analysis gives an example of a generated response assigning a book to the wrong author. These support the claim that facts can be mixed up, but the paper does not say the entities involved are similar. The supplied passages do not provide page numbers. (LLM, conf=0.83)
- Supportedcites [233] [233] Kurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela, and Jason Weston. 2021. Retrieval Augmentation Reduces Hallucination in Conversation. EMNLP (2021). - source
The Introduction states that language models often mix up facts between two similar entities when generating factually incorrect statements. This directly supports the cited description of the resulting error. (LLM, conf=0.92)
plainstates a cause- 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.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“As a result, the target reference may contain information that cannot be supported by the source [198, 268].”
What the sources say
- Supportedcites [198] [198] Ankur Parikh, Xuezhi Wang, Sebastian Gehrmann, Manaal Faruqui, Bhuwan Dhingra, Diyi Yang, and Dipanjan Das. 2020. ToTTo: A Controlled Table-To-Text Generation Dataset. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) . 1173-1186. - source
The Dataset section says that reference targets selected from web sentences may contain information that cannot be inferred from the source. The Data Annotation Process section also describes deleting phrases unsupported by table cells. (LLM, conf=0.93)
- Supportedcites [268] [268] Hongmin Wang. 2019. Revisiting Challenges in Data-to-Text Generation with Fact Grounding. In Proceedings of the 12th International Conference on Natural Language Generation . 311-322. - source
The Introduction reports that about 40% of human-written game-summary content cannot be directly mapped to the input boxscore records and draws on information beyond those inputs. Section 2.1 likewise describes reference content not licensed by the boxscore table. This supports the claim that a target reference may contain information the source does not support. (LLM, conf=0.93)
hedgedstates a possible cause- 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.
- Supported
117 more claims · 74 with their cited sources checked
Create a free account to see all 304 claims and to verify the 2 references still open.
- Borderline: one of the tests for a substantial claim is unclear. 1
- It may state two separate claims as one. 90
- Probably not a substantial claim. 142
- The quote only partly states this claim. 1
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Hallucination can lead to serious consequences such as incorrect or misleading code, security risks, and ethical issues [186].”
From A survey on large language model based autonomous agents (2024) · cites this paper as [186]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“citation fabrication constitutes a form of extrinsic hallucination in the absence of retrieval augmentation, since the model generates references not grounded in any provided source material [4].”
From How LLMs Cite and Why It Matters: A Cross-Model Audit of Reference Fabrication in AI-Assisted Academic Writing and Methods to Detect Phantom Citations (2026) · cites this paper as [4]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Recent taxonomic work distinguishes at least seven cases [15,18].”
From Hallucination as epistemic pollution: epistemic injustice and credibility in futures-oriented science education (2026) · cites this paper as [18]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“LLMs struggle to generate accurate and up-to-date responses on current topics, due to outdated knowledge, lack of domain-specific expertise, or hallucination13–17.”
From Leveraging long context in retrieval augmented language models for medical question answering (2025) · cites this paper as [16]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Fine-tuning can enrich LLMs with domain knowledge, enhance their specific ability, improve the fairness and reliability of the outputs, and prevent certain damage caused by hallucination [26].”
From FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning (2024) · cites this paper as [26]
Experimental — accuracy not yet measured
41 more claims about this paper
Create a free account to see every claim other papers make about this one.
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
§ Extrinsic Object Hallucination
“CHAIR (Caption Hallucination Assessment with Image Relevance) metric, which calculates what proportion of object words generated are actually in the image according to the ground truth captions.”
§ Extrinsic Object Hallucination
“CHAIR 𝑖 measures per-instance object hallucination, i.e. what fraction of object instances in each generated caption are hallucinated.”
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
§ 7.1 Hallucination Definition in Abstractive Summarization
“For instance, in Table 1, given the input article shown in the caption, an example of intrinsic hallucination is ' The Ebola vaccine was rejected by the FDA in 2019, '”
§ 2.1 Categorization
“in the abstractive summarization task from Table 1, the generated summary ' The first Ebola vaccine was approved in 2021 ' contradicts the source content”
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
§ Survey of Hallucination in Natural Language Generation
“The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions; (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, machine translation, and visual-language generation; and (3) hallucinations in large language models (LLMs)”
§ 1 INTRODUCTION
“The third part discusses this phenomenon in LLMs in Section 13.”
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 3×
“Recently, the rapid development of NLG has captured the imagination of many thanks to the advances in deep learning technologies, especially Transformer [189]-based models like BERT [29], BART [100], GPT-2 [149], and GPT-3 [16].”
BackgroundAn Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
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
Advances in Neural Information Processing Systems 29
Teymur, O., Zygalakis, K., & Calderhead, B. (2016) · Cited by 13,887
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · cited 1×
“This work investigates the performances of GPT-3 [13], GPT-Neo/J [141], GPT-2 [105] and a T5-based model [106].”
BackgroundAdvances in Neural Information Processing Systems 14: Proceedings of the 2001 Conference
(2002) · The MIT Press eBooks · doi:10.7551/mitpress/1120.001.0001 · Cited by 8,890
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821 · cited 1×
“Recently, the development of NLG has conquered the imagination of many thanks to the advances in deep learning technologies, especially the Transformer [159]-based models like BERT [24], BART [83], GPT-2 [127], and GPT3 [13].”
BackgroundLewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2019) · arXiv · doi:10.48550/arxiv.1910.13461 · Cited by 8,816 · cited 1×
“Recently, the development of NLG has conquered the imagination of many thanks to the advances in deep learning technologies, especially the Transformer [159]-based models like BERT [24], BART [83], GPT-2 [127], and GPT3 [13].”
Background
Research works printed but not linked: 16
- [4] Joshua Albrecht and Rebecca Hwa. 2007. A Re-examination of Machine Learning Approaches for Sentence-Level MT Evaluation. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics . Association for Computational Linguistics, Prague, Czech Republic, 880-887. https://aclanthology.org/P07-1111 -
- [16] Andrzej Białecki, Robert Muir, Grant Ingersoll, and Lucid Imagination. 2012. Apache lucene 4. In SIGIR 2012 workshop on open source information retrieval . 17. -
- [53] Yilun Du, Shuang Li, Antonio Torralba, Joshua B Tenenbaum, and Igor Mordatch. 2023. Improving Factuality and Reasoning in Language Models through Multiagent Debate. In Forty-first International Conference on Machine Learning . -
- [121] Philipp Koehn and Rebecca Knowles. 2017. Six Challenges for Neural Machine Translation. In First Workshop on Neural Machine Translation . Association for Computational Linguistics, 28-39. -
- [145] Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In ICML . -
- [149] Tian Li, Ahmad Beirami, Maziar Sanjabi, and Virginia Smith. 2020. Tilted Empirical Risk Minimization. In International Conference on Learning Representations . -
- [164] Jiasen Lu, Jianwei Yang, Dhruv Batra, and Devi Parikh. 2018. Neural Baby Talk. In CVPR . -
- [165] Yukun Ma, Khanh Linh Nguyen, Frank Z Xing, and Erik Cambria. 2020. A Survey on Empathetic Dialogue Systems. Information Fusion 64 (2020), 50-70. -
- [175] Marianna J. Martindale, Marine Carpuat, Kevin Duh, and Paul McNamee. 2019. Identifying Fluently Inadequate Output in Neural and Statistical Machine Translation. In MTSummit . -
- [179] Kathleen McKeown. 1992. Text Generation . Cambridge University Press. -
- [209] Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. OpenAI Blog 1, 8 (2019), 9. -
- [238] Hui Su, Xiaoyu Shen, Sanqiang Zhao, Zhou Xiao, Pengwei Hu, Cheng Niu, and Jie Zhou. 2020. Diversifying Dialogue Generation with Non-Conversational Text. In 58th Annual Meeting of the Association for Computational Linguistics . ACL, 7087-7097. -
- [256] Zhaopeng Tu, Yang Liu, Lifeng Shang, Xiaohua Liu, and Hang Li. 2017. Neural Machine Translation with Reconstruction. In Thirty-First AAAI Conference on Artificial Intelligence . -
- [261] Neeraj Varshney, Wenlin Yao, Hongming Zhang, Jianshu Chen, and Dong Yu. 2023. A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation. CoRR abs/2307.03987 (2023). https://doi.org/10.48550/arXiv.2307.03987 arXiv:2307.03987 - · arXiv · doi:10.48550/arxiv.2307.03987 · Paper page
- [285] Zeqiu Wu, Michel Galley, Chris Brockett, Yizhe Zhang, Xiang Gao, Chris Quirk, Rik Koncel-Kedziorski, Jianfeng Gao, Hannaneh Hajishirzi, Mari Ostendorf, et al. 2021. A Controllable Model of Grounded Response Generation. In Proceedings of the AAAI Conference on Artificial Intelligence , Vol. 35. 14085-14093. -
- [291] Xinnuo Xu, Ondřej Dušek, Verena Rieser, and Ioannis Konstas. 2021. AGGGEN: Ordering and Aggregating while Generating. roceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL2021) (2021). -
Cited by
Items 2,701–2,800 of 4,844
Agard, G., Bianchi, A., Bernat, M., et al. (2024) · Anesthésie & Réanimation · doi:10.1016/j.anrea.2023.12.001
Design of Machine Automatic Translation System Based on Artificial Intelligence
Huang, J., & Liu, S. (2023) · International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics (AIKIIE) · doi:10.1109/aikiie60097.2023.10390173 · Cited by 1
“The purpose of this study is to enhance collaboration among scholars in order to address the problem of illusory text in machine translation[6].”
BackgroundA Coarse and Fine Grained Masking Approach for Video-Grounded Dialogue
Xu, F., Zhou, W., Sun, T., Lu, J., Yu, Z., & Li, G. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-53308-2_30
Student-Teacher Prompting for Red Teaming to Improve Guardrails
Llaca, R. R., Leskoschek, V., Paiva, V. C., Lupău, C., Lippmann, P., & Yang, J. (2023) · doi:10.18653/v1/2023.artofsafety-1.2 · Cited by 5
Unsupervised Topic-Conditional Extractive Summarization
Malkiel, I., Yehuda, Y., Ephrath, J., Kats, O., Barkan, O., Nice, N., & Koenigstein, N. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447347
“These methods are limited by text size and may produce un-11286 intended content [12].”
MethodAlleviating Hallucinations Via Supportive Window Indexing in Abstractive Summarization
Duan, J., Lu, F., & Liu, J. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446022
Fact-CoT: Explicit Fact-Enhanced Chain-of-Thought Prompting for Commonsense Reasoning
Dai, L., & Qin, K. (2023) · International Conference on Computer Science and Automation Technology (CSAT) · doi:10.1109/csat61646.2023.00092 · Cited by 1
How Does ChatGPT Perform on the Italian National Residency Program Admission Test?Preprint
Barone, G., Confalonieri, F., Gaeta, A., Ferraro, V., Vinciguerra, P., & Maria, A. D. (2024) · Preprints.org · doi:10.20944/preprints202403.1684.v1
Xu, S., Chen, S., & Chen, M. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-1280-9_9
Intertwining Two Artificial Minds: Chaining GPT and RoBERTa for Emotion Detection
Kok-Shun, B. V., Chan, J., Peko, G. M., & Sundaram, D. (2023) · IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE) · doi:10.1109/csde59766.2023.10487718 · Cited by 3
Measuring hallucination in disentangled representations
Benazha, H., Ayache, S., Kadri, H., et al. (2024) · doi:10.1109/ijcnn60899.2024.10651269
“In the text domain, the recent large language models literature showed that generative models can lead to hallucination, i.e. generating incorrect but plausible data [22], which may be caused by bad data sources or suboptimal training [23].”
BackgroundSimulation of Structured Natural Language Algorithm on Cloud Computing
Fang, Q., & Tang, K. (2024) · IEEE International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA) · doi:10.1109/eebda60612.2024.10485753
“…generate natural language text, calculate the complexity or continuity of the text, etc. Information retrieval uses natural language technology to retrieve relevant information from large-scale text data, which includes tasks such as text indexing, query processing, and correlation sorting [6-7].”
BackgroundGuan, K., & Zhang, Y. (2023) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa-bdcloud-socialcom-sustaincom59178.2023.00161 · Cited by 1
Joo, E., Lee, D. K., Youn, J., Sung, J.-W., & Choi, H. (2024) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp60711.2024.00071
“Recent models like RAG and FiD play a crucial role in leveraging relevant knowledge, addressing issues like LM hallucinations during text generation [4], [5], [6].”
BackgroundThreats or Opportunities? Enhancing Firm Performance in the Era of Generative AIPreprint
Lee, S. J., Lehmann, J., Chae, H., Shin, D.-H., Auh, S., & Han, S. P. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4771103
Lucke, A., Johannes, H., Bielefeld, U., & DHd-Verband (2024) · Digital humanities · doi:10.1515/9783839470039
Towards human-level artificial intelligence agents
Leung, J. C. (2024) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/174532 · Cited by 1
Szabó, Z. (2024) · SZTE Repository of Dissertations (University of Szeged) · doi:10.14232/phd.11883
A Framework for Enhancing Behavioral Science Research with Human-Guided Language Models
Scheuerman, J., & Acklin, D. (2024) · Proceedings of the AAAI Symposium Series · doi:10.1609/aaaiss.v3i1.31206 · Cited by 2
User Stories Extraction from Natural Language: Assessing and Improving Llm's Results AccuracyPreprint
Khalil, A., Ettifouri, E. H., Saber, M., & Belkasmi, M. G. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4830008
QuDial: A Quadruple-driven Dialogue System for Real Estate Consulting Services
Yang, S., Chen, H., & Fang, B. (2024) · International Conference on Machine Learning and Computing (ICMLC) · doi:10.1145/3651671.3651759 · Cited by 1
When the occasion comes, the proverb comes: value alignment via proverbial bank and synthetic rules
Salaam, C., & Rawat, D. B. (2024) · Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications · doi:10.1117/12.3014236
“9 Fundamentally, the causes of hallucinations can be linked to a mismatch between the implicit knowledge that is learned through the pre-training steps and the actual knowledge required for the task.”
BackgroundAyuda, F. G. (2024) · Scire representación y organización del conocimiento · doi:10.54886/scire.v30i1.5005 · Cited by 2
Navigating the Digital Turn (Again): ChatGPT and Large Language Models in Anthropological EducationPreprint
Hau, M. F. (2024) · SocArXiv (OSF Preprints) · doi:10.31235/osf.io/h76tp
Vie-Net: Regressive U-Net for Vegetation Index EstimationPreprint
Capparella, V., Nemmi, E. N., Violino, S., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4873658
Benchmarking Biomedical Relation Knowledge in Large Language Models
Zhang, F., Yang, K., Zhao, C., Li, H., Xin, D., Tian, H., & Zhou, X. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5131-0_41 · Cited by 1
Yifeng, P. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4885346
CIQA: A Coding Inspired Question Answering Model
Arraf, M., & Radinsky, K. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657830
Grasping Both Query Relevance and Essential Content for Query-focused Summarization
Xiong, Y., Kamigaito, H., Murakami, S., Zhang, P., Takamura, H., & Okumura, M. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657958 · Cited by 1
LLM-Enhanced Theorem Proving with Term Explanation and Tactic Parameter Repair✱
Liu, X., Liu, H., Yi, X., & Wang, J. (2024) · Asia-Pacific Symposium on Internetware · doi:10.1145/3671016.3674823
Studying the Knowledge and Behavior of ChatGPT via Journey to the West
Zhou, Z. (2024) · IEEE International Conference on Big Data Security on Cloud, IEEE International Conference on High Performance and Smart Computing, and IEEE International Conference on Intelligent Data and Security (BigDataSecurity/HPSC/IDS) · doi:10.1109/hpsc62738.2024.00012
“Besides the well-known fact that LLMs may provide factually incorrect information (usually known as hallucination [7]) which is still an open challenge.”
BackgroundBigQA: A Software Reference Architecture for Big Data Question Answering Systems
Moraes, L. M. P., Jardim, P. C., & Ciferri, C. D. D. A. (2024) · Lecture notes in business information processing · doi:10.1007/978-3-031-64748-2_3
Plausibel, aber unwahr: Sozialisation und Wahrscheinlichkeitspapageien
Bellon, J. (2024) · Techno:Phil · doi:10.1007/978-3-662-68021-6_8
Ok, C., Lee, E., Ju, H., Lee, J., & Oh, D. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115961 · Cited by 1
A Progressive Question Answering Framework Adaptable to Multiple Knowledge Sources
Zhan, Y., Li, Y., Zhang, M., & Zou, L. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-7244-5_26 · Cited by 1
A Unified Data Augmentation Framework for Low-Resource Multi-domain Dialogue Generation
Liu, Y., Nie, E., Feng, S., Hua, Z., Ding, Z., Wang, D., Zhang, Y., & Schütze, H. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70344-7_10 · Cited by 1
Wu, Y., & Henriksson, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70352-2_12
DEE: Dual-Stage Explainable Evaluation Method for Text Generation
Zhang, S., Li, Y., Wu, R., Huang, X., Chen, Y., Xu, W., & Qi, G. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5575-2_29 · Cited by 3
Bascik, T., & Pham-Dang, S. (2024) · Documentation et bibliothèques · doi:10.7202/1112894ar
The Wade Test: Generative AI and a CEO botPreprint
Choudhury, P., Vanneste, B. S., & Zohrehvand, A. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4945933 · Cited by 2
Li, S., Wong, K. W., Zhu, D., & Fung, C. C. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650447 · Cited by 2
“LLMs implicitly encode knowledge within their parameters, making it challenging to interpret or validate the information they generate [3], [4].”
BackgroundCase-Based Deduction for Entailment Tree Generation
Shi, J., Ding, X., & Liu, T. (2024) · Mathematics · doi:10.3390/math12182893 · Cited by 1
KELTP: Keyword-Enhanced Learned Token Pruning for Knowledge-Grounded Dialogue
Wang, X. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72350-6_16
Gan, C., Zhang, Q., & Mori, T. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70242-6_5 · Cited by 2
Rui, T., Zhu, M., Cao, H., & Ren, H. (2024) · Forests · doi:10.3390/f15091670
Ethical Considerations and Challenges
(2024) · Advances in knowledge acquisition, transfer, and management book series/Advances in knowledge acquisition, transfer and management book series · doi:10.4018/979-8-3693-6905-0.ch007 · Cited by 3
LLM-PQA: LLM-enhanced Prediction Query Answering
Li, Z., Zhao, W., Katsifodimos, A., et al. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679210
Abdullah, M. H. A., Aziz, N., Abdulkadir, S. J., Hussain, K., Alhussian, H., & Talpur, N. (2024) · Journal of Data and Information Science · doi:10.2478/jdis-2024-0029 · Cited by 2
Analyzing Sweep Integration in GitHub for AI-Augmented Issue Resolution
Utomo, M. M., Kusumo, D. S., & Richasdy, D. (2024) · doi:10.1109/icoict61617.2024.10698190
Lee, Z., Huang, Z., Yao, Z., et al. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679229
Unified Argument Retrieval System from German News Articles Using Large Language Models
Piriyatamwong, P., Kalloori, S., & Zünd, F. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679232
ChatGPT—A Review of a Powerful Language Model for Conversational AI
Jagnade, G., Sable, S., & Ikar, M. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-97-5866-1_21
ProSide: Knowledge Projector and Sideway for Pre-trained Language Models
He, C., Lu, G., & Shen, L. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-9434-8_5
Element-Centered Multi-granularity Network for Dense Video Captioning
Dang, X., Wang, G., Wu, X., & Qin, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-8792-0_31
Llm-Empowered Literature Mining for Material Substitution Studies in Sustainable ConcretePreprint
Duan, Y., Tian, Y., Ghosh, S., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.5017239
Zhao, H., Han, Z., Yin, S., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.5020497
Ammar, A. S. (2024) · Springer eBooks · doi:10.1007/978-3-031-71477-1_1
Hitchhiker's Introduction to Model RiskPreprint
Jadoon, A. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4997231
Déjà Vu: Uncanny and Serendipitous Re-encountering of Audiovisual Archives
Yang, Y. (2024) · doi:10.1145/3680530.3695438
“Second, the design of the decoding strategy itself, such as the use of the top-k sampling to enhance diversity, can inadvertently increase the likelihood of hallucinations [Dziri et al. 2021; Ji et al. 2023].”
Chai, Y., Cui, F., Yu, S., Jiang, Y., Liu, H., & Liu, Y. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.5026989
Chusova, A. E., Artemieva, I. L., & Chusov, A. A. (2024) · International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON) · doi:10.1109/sibircon63777.2024.10758538 · Cited by 2
Probing the Reasoning Abilities of Llms in Blocks WorldPreprint
Zhao, K. Z., & Macbeth, J. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.5038600
Feature Extraction for Claim Check-Worthiness Prediction Tasks Using LLM
Teramoto, Y., Komamizu, T., Matsushita, M., & Hatano, K. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78090-5_5 · Cited by 1
Agent-Enhanced Large Language Models for Researching Political InstitutionsPreprint
Loffredo, J., & Yun, S. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.5053570
Building and Leveraging Domain-specific Pre-trained Models to Support Japanese News Summarization
Ishihara, S., Murata, E., Nakama, Y., & Takahashi, H. (2024) · Journal of Natural Language Processing · doi:10.5715/jnlp.31.1717
Foundations of Generative Information Retrieval
Ai, Q., Zhan, J., & Liu, Y. (2024) · The information retrieval series · doi:10.1007/978-3-031-73147-1_2 · Cited by 5
The Impact of Varying Knowledge on Question-Answering System
Ha, A. N. T., Quoc, T. N., Van, T. N., Trung, H. P., Hoang, V. T., & Le-Viet, T. (2024) · Asian Conference on Communication and Networks (ASIANComNet) · doi:10.1109/asiancomnet63184.2024.10811070
Anaguchi, F., Chakraborty, S., Morita, T., Egami, S., Ugai, T., & Fukuda, K. (2024) · International Symposium on Computing and Networking · doi:10.1109/candar64496.2024.00010
Understanding the Roles of Visual Modality in Multimodal Dialogue: An Empirical Study
Cao, Q., Song, R., & Chen, X. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-2071-5_20
Fontana, A., Sinatti, G., Cicchinelli, S., Santini, S. J., Caputo, V., Letteri, I., Vittorini, P., & Balsano, C. (2024) · International Conference on Information Technology Based Higher Education and Training (ITHET) · doi:10.1109/ithet61869.2024.10837651
“At the same time, a sound evaluation process can enhance and uphold validation and consistency, preventing common mistakes [15].”
LP-LM: No Hallucinations in Question Answering with Logic Programming
Wu, K., & Liu, Y. A. (2025) · Electronic Proceedings in Theoretical Computer Science · doi:10.4204/eptcs.416.5 · Cited by 1
“Large language models (LLMs) hallucinate, i.e., generate information that appears plausible but is fac-tually incorrect [9].”
Quit Playing Language Games with My Heart; or, Conversational AI and Knowledge Sharing
McGrath, L. S. (2024) · Ethnographic Praxis in Industry Conference Proceedings · doi:10.1111/epic.12205
Cyber Risk, ChatGPT and Firm ValuePreprint
Kearney, F., Ma, T., Movaghari, H., & Sermpinis, G. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5068625
Is ChatGPT Ready for Indian-Language Speakers? Findings From a Preliminary Mixed Methods Study
Chaitra, C. R., Upadhyay, P., & Chakraborty, D. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-80829-6_9 · Cited by 1
On the Potential of Large Language Models in Parallel Systems: A Systematic Analysis
Cheng, X., Luo, S., Yang, J., Lei, Y., Li, Z., & Yang, L. (2024) · China Automation Congress (CAC) · doi:10.1109/cac63892.2024.10864500
“Firstly, hallucination is widely recognized as a significant drawback of LLMs [47], leading them to generate incorrect, nonsensical, or unrealistic content due to their limited ability to effectively utilize internal and external knowledge during task-solving.”
Intelligent Q&A System for Ventilators Based on Knowledge Graph-Enhanced LLM
Ma, C., Zheng, Z., Yao, Q., Li, W., Xu, R., He, J., & Duan, Y. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-1395-3_17
Chen, Y., Sun, J., Dong, M., Meng, Z., Yang, Y., Muhetaier, A., Li, C., & Qin, J. (2025) · doi:10.2196/preprints.70967
Derivation Prompting: A Logic-Based Method for Improving Retrieval-Augmented Generation
Sastre, I., Moncecchi, G., & Rosá, A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-80366-6_34 · Cited by 1
“This lack of control can lead to erroneous reasoning and susceptibility to hallucinations, which are well-known problems when working with LLMs [13,5].”
Low Liquidity Brings Volatility: Quantum Zeno Effect and Pricing
Widdows, D., & Pothos, E. M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-83117-1_36
WIP: Pledging to be an Ethical Computing Professional
Dasigi, V. G., Estell, J. K., & Christensen, K. J. (2024) · IEEE Frontiers in Education Conference (FIE) · doi:10.1109/fie61694.2024.10893565
“Large language models, such as ChatGPT [11], have garnered widespread attention due to their impressive performance in many contexts but can generate “hallucinations” – inaccurate unintended text [12].”
Arsic, P., & Mayer, C. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.02.26.640343
“Hallucination is a major concern in generative artificial intelligence (see e.g. Ji et al. 2023).”
Winberg, D., Xuan, D., Tang, T., & Shi, L. (2025) · Pharmacoeconomics and Policy · doi:10.1016/j.pharp.2025.03.003 · Cited by 4
User Issues and Concerns in Generative AI: A Mixed-Methods Analysis of App Reviews
Bracamonte, V., Löbner, S., Tronnier, F., Lieberknecht, A.-K., & Pape, S. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-82633-7_19
Adaptive Factual Decoding for Hallucination Mitigation with Part-of-Speech Based Critics
Zhao, C., He, S., Xu, H., Liang, P., Zhao, J. L., & Liu, K. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-1809-5_21 · Cited by 1
Mitigating Multimodal Large Language Model Hallucinations Through Direct Preference Optimization
Yang, Y., & Zhang, J. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2914-5_23
Solórzano, R. S., & Cerquedo, D. E. B. (2025) · Biblioteca Universitaria · doi:10.22201/dgbsdi.0187750xp.2024.2.1554
Pan, Z., Peng, Y.-H., Jian, Z.-Q., Chen, Y.-H., Qiu, W.-T., Ma, H.-N., Yao, J.-F., Wang, M., & Wu, Q.-Q. (2025) · IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp49660.2025.10890213 · Cited by 1
Yue, T., Xiao, M., Zhang, D., Liu, X., Li, Y., & Wang, S. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890678 · Cited by 1
“This bottleneck also makes it difficult to handle visual scenes containing numerous frames or long-term continuity, often leading to the emergence of “hallucinations” [21]–[23].”
Enhancing Digital Libraries with Automated Definition Generation
Zielinski, A., Hirzel, S., & Arnold-Keifer, S. (2024) · ACM/IEEE Joint Conference on Digital Libraries · doi:10.1145/3677389.3702536 · Cited by 1
Estimating the Confidence of Language Model Generation using Training Data
Yoshikawa, H., & Okazaki, N. (2025) · Journal of Natural Language Processing · doi:10.5715/jnlp.32.91
Comparison of Relation Extraction Models for Generating Knowledge Graphs in the Oil Drilling Domain
Ticianeli, G. H. G., Cândido, A., Guilherme, I. R., Penteado, B. E., Perrout, S. R., Morelli, L. H., Paiola, P. H., & Garcia, G. L. (2024) · doi:10.5753/eniac.2024.245094 · Cited by 1
Graph Convolutional Networks with Fine-Tuned Word Representations for Visual Question Answering
Owusu, J. W., Zakari, R. Y., Qin, K., & He, T. (2024) · IEEE Smart World Congress (SWC) · doi:10.1109/swc62898.2024.00214 · Cited by 2
“The proposed framework is rigorously evaluated using the GQA [34] and VQA 2.0 datasets, which are both widely recognized and publicly available benchmarks for visual question answering research.”
InfluentialOverview of the Comprehensive Evaluation of Large Language Models
Lin, L., Zhu, D., & Shang, J. (2024) · IEEE Smart World Congress (SWC) · doi:10.1109/swc62898.2024.00231 · Cited by 2
“A comprehensive test of the model's reliability, including accuracy, hallucination[12], consistency, interpretability, and calibration error, is essential for ensuring its appropriate application in critical fields.”
Navigating the CISO’s Mind by Integrating GenAI for Strategic Cyber Resilience
Grigaliūnas, Š., Brūzgienė, R., Driaunys, K., Danielienė, R., Veitaitė, I., Astromskis, P., Nemickienė, Ž., Vengalienė, D., Lopata, A., Andrijauskaitė, I., et al. (2025) · Electronics · doi:10.3390/electronics14071342 · Cited by 1
Hwang, H., Wong, R., Lim, D., Kang, J., & Joe, I. (2025) · IEEE Access · doi:10.1109/access.2025.3555272
Chan, Y.-C., Huang, P., Chen, Z.-L., Wang, C.-N., Lin, W., Chiu, J.-P., Chiu, Y.-C., Lin, Y.-H., Huang, E. T. C., See, S. C. W., et al. (2025) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-031-86323-3_38 · Cited by 1
Prabodhini: Making Large Language Models Inclusive for Low-Text Literate Users
Jain, V., Vishnuvajjala, S., Voora, P., Bikkina, B. R., Boddapati, B., Chaitra, C. R., Chakraborty, D., & Upadhyay, P. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88717-8_35
The development and evaluation of an automatic clitic generator for Pashto language
Din, A., Rabbi, I., Farooq, U., et al. (2025) · Humanities and Social Sciences Communications · doi:10.1057/s41599-025-04516-5
“…using reinforcement learning (Chung et al., 2024), text generation from given data using neural planning (Puduppully, 2022), application of recurrent convolutional neural networks for text generation (Ji et al., 2023) and automatic text generation using deep learning algorithms (Du et al., 2023).”
On the Complexities of Enabling Demonstrated Consent
Alexiou, P., Azzopardi, J., Bajada, C. J., Ebejer, J.-P., Martin, G. M., & Pace, N. P. (2025) · The American Journal of Bioethics · doi:10.1080/15265161.2025.2470694
Metadata
- Authors
- Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P.
- Affiliations
- Hong Kong University of Science and Technology (HK)
- ORCID
- Venue
- ACM Computing Surveys
- Published
- 2023-03-03
- Volume
- 55
- Issue
- 12
- Pages
- 1-38
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W4309674289
- Semantic Scholar
- 3def68bd0f856886d34272840a7f81588f2bc082
- Cited by
- 5,025
- References
- 111
- Citations by year
- 2026: 2296 · 2025: 1441 · 2024: 817 · 2023: 453
- FWCI
- 224.36
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Computing Surveys (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- hallucinations, natural language generation, hallucination mitigation, abstractive summarization, dialogue generation, generative question answering, data-to-text generation, machine translation, large language models, transformer models
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-09-30, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-09-30 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.




