My Bad! Repairing Intelligent Voice Assistant Errors Improves Interaction
The DOI matches its Crossref record; 61 of the 61 references it cites were found in a registry or an index.
Abstract
One key technique people use in conversation and collaboration is conversational repair. Self-repair is the recognition and attempted correction of one's own mistakes. We investigate how the self-repair of errors by intelligent voice assistants affects user interaction. In a controlled human-participant study (N =101), participants asked Amazon Alexa to perform four tasks, and we manipulated whether Alexa would "make a mistake'' understanding the participant (for example, playing heavy metal in response to a request for relaxing music) and whether Alexa would perform a correction (for example, stating, "You don't seem pleased. Did I get that wrong?'') We measured the impact of self-repair on the participant's perception of the interaction in four conditions: correction (mistakes made and repair performed), undercorrection (mistakes made, no repair performed), overcorrection (no mistakes made, but repair performed), and control (no mistakes made, and no repair performed). Subsequently, we conducted free-response interviews with each participant about their interactions. This study finds that self-repair greatly improves people's assessment of an intelligent voice assistant if a mistake has been made, but can degrade assessment if no correction is needed. However, we find that the positive impact of self-repair in the wake of an error outweighs the negative impact of overcorrection. In addition, participants who recently experienced an error saw increased value in self-repair as a feature, regardless of whether they experienced a repair themselves.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Certain domains are aligned with particular platform types, indicating specialised applications e.g. the smart home assistance domain was associated with devices such as Amazon Alexa [6, 17, 19, 33, 46, 60], the INSPIRE system [74], and devices not specified [38].”
From System and User Strategies to Repair Conversational Breakdowns of Spoken Dialogue Systems: A Scoping Review (2024) · cites this paper as [19]
In the citing paper
“A study by Cuadra et al. [16] found that when voice assistants make mistakes, voice assistant self-repair greatly improves people's assessment of an intelligent voice assistant, but it can have the opposite impact if no correction is needed.”
From A Mixed-Methods Approach to Understanding User Trust after Voice Assistant Failures (2023) · cites this paper as [16]
In the citing paper
“which has been shown to improve users' assessment of VAs [16].”
From Situated Understanding of Errors in Older Adults' Interactions with Voice Assistants: A Month-Long, In-Home Study (2026) · cites this paper as [16]
In the citing paper
“However, excessive correction can degrade user perceptions [16].”
From Situated Understanding of Errors in Older Adults' Interactions with Voice Assistants: A Month-Long, In-Home Study (2026) · cites this paper as [16]
Citations
Cites
Using thematic analysis in psychology
Braun, V., & Clarke, V. (2006) · Qualitative Research in Psychology · doi:10.1191/1478088706qp063oa · Cited by 194,414
Qualitative Data Analysis: A Methods Sourcebook
Miles, M. B., Huberman, A. M., & Saldaña, J. (1988) · Cited by 20,701
A very brief measure of the Big-Five personality domains
Gosling, S. D., Rentfrow, P. J., & Swann, W. B. (2003) · Journal of Research in Personality · doi:10.1016/s0092-6566(03)00046-1 · Cited by 8,307
The Preference for Self-Correction in the Organization of Repair in Conversation
Schegloff, E. A., Jefferson, G., & Sacks, H. (1977) · Language · doi:10.2307/413107 · Cited by 5,150
Ekman, P. (1976) · Medical Entomology and Zoology · Cited by 4,345
Lucey, P., Cohn, J. F., Kanade, T., Saragih, J., Ambadar, Z., & Matthews, I. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops · doi:10.1109/cvprw.2010.5543262 · Cited by 4,303 · cited 1×
“…technology via visual cues can be fore-shadowed by the widespread availability of emotional expression image databases such as Ekman’s Pictures of Facial Affect [21], the Belfast database [19], the Extended Cohn-Kanade Dataset [37], or the Affectiva-MIT Facial Expression Dataset [38].”
BackgroundThe Repertoire of Nonverbal Behavior: Categories, Origins, Usage, and Coding
EKMAN, P., & FRIESEN, W. V. (1969) · Semiotica · doi:10.1515/semi.1969.1.1.49 · Cited by 3,316
Embodied Conversational Agents
(2000) · The MIT Press eBooks · doi:10.7551/mitpress/2697.001.0001 · Cited by 1,799
Clark, H. H., & Schaefer, E. F. (1989) · Cognitive Science · doi:10.1207/s15516709cog1302_7 · Cited by 1,699
Finding usability problems through heuristic evaluation
Nielsen, J. (1992) · Proceedings of the SIGCHI conference on Human factors in computing systems - CHI '92 · doi:10.1145/142750.142834 · Cited by 1,060
Research works printed but not linked: 11
- Susan E Brennan et almbox. 2005. How conversation is shaped by visual and spoken evidence. Approaches to studying world-situated language use: Bridging the language-as-product and language-as-action traditions (2005), 95--129.
- 10.5555/371552.371555 · doi:10.5555/371552.371555
- The Economist. 2017. Terry Winograd: Where Humans still Beat Computers. The Economist (Jan 2017).
- Yuan Fan and Qiuchen Wang. 2013. Robot. US Patent App. 29/431,926.
- Petra Gieselmann. 2006. Comparing error-handling strategies in human-human and human-robot dialogues. In Proc. 8th Conf. Nat. Language Process.(KONVENS). Konstanz, Germany. 24--31.
- 10.5555/974305.974334 · doi:10.5555/974305.974334
- Harvey Sacks, Emanuel A Schegloff, and Gail Jefferson. 1978. A simplest systematics for the publisher of turn taking for conversation. In Studies in the publisher of conversational interaction. Elsevier, 7--55.
- Emanuel A Schegloff. 1997 a. Practices and actions: Boundary cases of other-initiated repair. Discourse processes, Vol. 23, 3 (1997), 499--545.
- Emanuel A Schegloff. 1997 b. Third turn repair. AMSTERDAM STUDIES IN THE THEORY AND HISTORY OF LINGUISTIC SCIENCE SERIES 4 (1997), 31--40.
- 10.1353/lan.1977.0041 · doi:10.1353/lan.1977.0041 · Paper page
- Bo Zhang, Qingsheng Cai, Jianfeng Mao, Eric Chang, and Baining Guo. 2001. Spoken dialogue management as planning and acting under uncertainty. In Seventh European conference on speech communication and technology.
Cited by
State-of-the-Art Human-Computer-Interaction in Metaverse
Lv, Z. (2023) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2023.2248833 · Cited by 115
“The effects of smart voice assistants ’ ability to fix their own mistakes on the user experience were investigated by Cuadra et al. (2021).”
A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration
Gao, J., Gebreegziabher, S. A., Choo, K. T. W., Li, T. J.-J., Perrault, S. T., & Malone, T. W. (2024) · Extended Abstracts of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613905.3650786 · Cited by 57
User Interaction Patterns and Breakdowns in Conversing with LLM-Powered Voice Assistants
Mahmood, A., Wang, J., Yao, B., Wang, D., & Huang, C.-M. (2025) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2024.103406 · Cited by 51
“As an AI language model, I cannot”: Investigating LLM Denials of User Requests
Wester, J., Schrills, T., Pohl, H., & van Berkel, N. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642135 · Cited by 100
“Their results suggest that participants perceived self-repairing VAs more positively [9].”
Do, H. J., Kong, H.-K., Tetali, P., Lee, J., & Bailey, B. P. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3579532 · Cited by 32
“found that repairs made users feel successful and less frustrated [20].”
BackgroundA Mixed-Methods Approach to Understanding User Trust after Voice Assistant Failures
Baughan, A., Wang, X., Liu, A., Mercurio, A., Chen, J., & Ma, X. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581152 · Cited by 32
“[16] found that when voice assistants make mistakes, voice assistant self-repair greatly improves people’s assessment of an intelligent voice assistant, but it can have the opposite impact if no correction is needed.”
BackgroundMethodInfluentialWenzel, K., Devireddy, N., Davison, C., & Kaufman, G. F. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581357 · Cited by 51
“Although around 20% of that study’s participants spoke English as a second language, the researchers did not focus on race as a factor in reporting or interpreting their results [21].”
BackgroundZubatiy, T., Mathur, N., Heck, L. P., Vickers, K. L., Rozga, A., & Mynatt, E. D. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3610170 · Cited by 40
“CAs ought to remember previous user errors over time and provide support to help the user avoid repeating the same mistakes as described in [13].”
BackgroundInfluentialVirtual Assistants: A Review of the Next Frontier in AI Interaction
Todericiu, I. A. (2025) · Acta Universitatis Sapientiae Informatica · doi:10.1007/s44427-025-00002-7 · Cited by 29
“To deliver a comprehensive evaluation of VA performance, various other metrics are frequently taken into account, including conversational flow, error management, personalization, multi-turn completion rate, and domain coverage [27–29].”
Phinnemore, R., Reza, M., Lewis, B., Mahadevan, K., Wang, B. K., Annett, M., & Wigdor, D. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581346 · Cited by 21
“and self-correcting conversational dialogues [17, 52].”
BackgroundMethodInfluentialTake a shot! Natural language control of intelligent robotic X-ray systems in surgery
Killeen, B. D., Chaudhary, S., Osgood, G. M., & Unberath, M. (2024) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-024-03120-3 · Cited by 24
Designing for Harm Reduction: Communication Repair for Multicultural Users' Voice Interactions
Wenzel, K., & Kaufman, G. F. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642900 · Cited by 34
“Lastly, our suggestion to redirect blame and employ brevity has been highlighted by other researchers [11, 23, 43], and we are excited to support innovation in this direction.”
BackgroundAlghamdi, E., Halvey, M., & Nicol, E. (2024) · ACM Conversational User Interfaces 2024 · doi:10.1145/3640794.3665558 · Cited by 36
“A number of studies (N=7) favoured semi-structured interviews [19, 34, 42, 50, 53, 77, 78] while others chose structured interviews [2] or did not specify interview format [6, 67].”
BackgroundMethodWei, C. Z., Kim, Y.-H., & Kuzminykh, A. (2023) · Proceedings of the 5th International Conference on Conversational User Interfaces · doi:10.1145/3571884.3597139 · Cited by 14
“…of the agent contains Godspeed questionnaire [3]’s set of questions on likeability used by [55], Subjective Assessment of Speech System Interface (SASSI) questionnaire [37]’s set of questions on likeability used by [7, 10] and questionnaire items like “ this voice agent was likeable ” used by [14].”
BackgroundMethodMarconi, L., Longo, L., & Cabitza, F. (2026) · Machine Learning and Knowledge Extraction · doi:10.3390/make8020028 · Cited by 29
Lin, G. E., Li, J. Y., Fazly, A., Pavlović, V., & Truong, K. N. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581006 · Cited by 13
“To improve the usability of voice interfaces, it is vital to address challenges beyond natural language-related errors like mishearing or misunderstanding users [15, 63].”
BackgroundBraggaar, A., Verhagen, J., Martijn, G., & Liebrecht, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-54975-5_2 · Cited by 19
“Conversely, customers face challenges in coping with the chatbot’s responses [6], resulting in customer frustration [13] and a decrease in overall customer satisfaction [23].”
BackgroundCho, S., Kim, Y., Jang, J., & Hwang, I. (2023) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3580812 · Cited by 14
“Proactive interactions have been studied extensively in push notifications [69, 95, 96, 108, 113, 116], proactive speakers [13, 17, 25, 72, 82, 83, 117, 144, 145], and interactive displays [5, 137, 142, 157, 159].”
Background"Uh, This One?": Leveraging Behavioral Signals for Detecting Confusion during Physical Tasks
Stiber, M., Bohus, D., & Andrist, S. (2024) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3678957.3685727 · Cited by 12
“Moreover, implementing these techniques requires perception and detection of explicit and implicit signals, so systems must be cautious to avoid excessive false positives, as these could degrade the interaction [12, 34].”
Exploring Familiarity and Knowledgeability in Conversational Virtual Agents
Yang, F., Guo, S., & Mousas, C. (2025) · ACM Transactions on Applied Perception · doi:10.1145/3757062 · Cited by 13
“Our finding aligns with Cuadra et al.’s [24] and Choi et al.’s [15] studies, which reported that their participants preferred error-free interaction with virtual agents.”
Working with troubles and failures in conversation between humans and robots: workshop report
Forster, F. M. C., Romeo, M., Holthaus, P., Wood, L. J., Dondrup, C., Fischer, J. E., Liza, F. F., Kaszuba, S., Hough, J., Nesset, B., et al. (2023) · Frontiers in Robotics and AI · doi:10.3389/frobt.2023.1202306 · Cited by 10
“…studies in HRI take place in controlled experimentalconditions,where“failures”areexplicitlydesignedand occur only at specific moments (Ragni et al., 2016; Washburn et al., 2020a; Cuadra et al., 2021; Green et al., 2022), instead of a natural occurrence of the interactions between humans and robots.”
BackgroundAlloatti, F., Grasso, F., Ferrod, R., Siragusa, G., Di, L., & Cena, F. (2024) · Computer Speech & Language · doi:10.1016/j.csl.2023.101603 · Cited by 12
Understanding User Preferences of Voice Assistant Answer Structures for Personal Health Data Queries
Rey, B., Sakamoto, Y., Sin, J., & Irani, P. (2024) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3640794.3665552 · Cited by 8
“For example, while factors like interruption [17] and conversational repair [12] have been explored, to our knowledge, only one work has explored answered structures for general VA use [20].”
BackgroundLv, N., Kannampallil, T., Xiao, L., Ronneberg, C. R., Kumar, V., Wittels, N. E., Ajilore, O., Smyth, J. M., & Ma, J. (2023) · JMIR Human Factors · doi:10.2196/49715 · Cited by 7
“This is consistent with the finding of a recent experimental study that showed that if a conversational agent offered opportunities for “conversational repair,” participants were more forgiving regarding their user interaction experience [28].”
ResultVoice Assistants' Accountability through Explanatory Dialogues
Alizadeh, F., Tolmie, P., Lee, M., Wintersberger, P., Pins, D., & Stevens, G. (2024) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3640794.3665557 · Cited by 6
“Similarly, Cuadra et al. [22] manipulated Alexa’s responses after mistakes to demonstrate that a VA’s ability to recognize and attempt to correct its own errors (self-repair) significantly enhances users’ perceptions of an intelligent voice assistant.”
BackgroundMoore, R. J., An, S., & Marrese, O. H. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3641026 · Cited by 15
“Subjects then rated how much the simulated interactions "feel successful" [6].”
BackgroundKontogiorgos, D. (2022) · Thesis Commons (OSF Preprints) · doi:10.31237/osf.io/fpts4 · Cited by 5
Meck, A.-M., Draxler, C., & Vogt, T. (2024) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2023.2266791 · Cited by 3
“When designing for HCI, looking at conversational equivalents in HHI is exceedingly helpful.”
InfluentialMore Than Words: The Impact of Voice Assistant Personality Traits on Failure Mitigation
Jayasiriwardene, S., Tag, B., Withana, A. I., & Sarsenbayeva, Z. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3749518 · Cited by 6
“This outcome was expected, given the significant body of research emphasizing the importance of failure mitigation in voice assistants [20–22, 49, 58, 59].”
Paradeda, R. B., Alves, Á. D. O., Torres, D., & Lima, A. (2024) · Journal on Interactive Systems · doi:10.5753/jis.2024.3725 · Cited by 4
“Although researchers have made significant progress in addressing the faulty behaviors exhibited by virtual assistants (Cuadra et al .”
BackgroundHe, T., & Jazizadeh, F. (2024) · ASCE International Conference on Computing in Civil Engineering (i3CE) · doi:10.1061/9780784485224.064 · Cited by 4
Mahmood, A., Wang, J., & Huang, C.-M. (2026) · ACM Transactions on Accessible Computing · doi:10.1145/3796236 · Cited by 6
“However, excessive correction can degrade user perceptions [18].”
Baumann, M., Markus, A., Pfister, J., Carolus, A., Hotho, A., & Wienrich, C. (2025) · Computers in Human Behavior Reports · doi:10.1016/j.chbr.2025.100610 · Cited by 3
Persuasiveness of Conversational Agents for Targeted Advertising: Autism and Gen-AI Chatbots
Chapman, K., Klabacka, K., Smith, G., & Page, X. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757645 · Cited by 2
“It has extended from computers and televisions [66] into chatbots [16, 56, 57, 63, 82], robots [30, 48, 77, 89, 90], and AI [53, 73, 106].”
Granting a Second Chance: How Recovery Strategies Shape Perceptions of Intelligent Agent Errors
Miao, X., Tang, J., Peng, K., & Wang, F. (2025) · IEEE RO-MAN · doi:10.1109/ro-man63969.2025.11217814 · Cited by 2
“Self-repair strategies, therefore, provide a promising solution for enhancing both warmth and competence in human-IA interactions [38].”
Enhancing intention understanding in voice assistants for older adults using large language models
Fu, J., Kang, C., Qian, Z., & Zhou, Y. (2026) · Behaviour and Information Technology · doi:10.1080/0144929x.2026.2615038 · Cited by 1
“These failures manifest in everyday interactions, for instance, playing the wrong music or failing to set reminders as expected (Cuadra et al. 2021).”
I Can Do It: Exploring Voice Assistants for Adults with Intellectual Disabilities
Nadeeshani, M., Johnstone, J., Ellis, K., & Ananthanarayan, S. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790573 · Cited by 2
“To address such issues, we recommend integrating repair mechanisms into VA systems, such as clarification prompts [23].”
Hu, J., Yao, X., Huang, Z., Liang, D., Yang, D., Liu, D., Li, J., Zhang, Y., & Ma, X. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3792787 · Cited by 3
“In addition, several papers explore CAs in more general scenarios, where CAs serve as all-purpose assistants for everyday tasks [94, 102], in smart speakers [133], or for driving cars [34].”
Guidelines for Bimodal Virtual Assistants
Carbajal-Pérez, C., Catalá, A., & Bugarín, A. (2022) · Nordic Conference on Human-Computer Interaction · doi:10.1145/3547522.3547688 · Cited by 1
“Recent researches [2, 8, 33] investigate how to improve conversational repair”
BackgroundDigital Modeling for Everyone: Exploring How Novices Approach Voice-Based 3D Modeling
Desolda, G., Esposito, A., Müller, F., & Feger, S. S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42293-5_11 · Cited by 5
“Self-repair strategies should be introduced to improve interaction [6].”
BackgroundHow to Convey Resilience: Towards a Taxonomy for Conversational Agent Breakdown Recovery Strategies
Feng, S. (2025) · Lecture notes in information systems and organisation · doi:10.1007/978-3-031-80119-8_18 · Cited by 1
Wong, A., Spyrou, J., & Fredericks, J. (2024) · Australian Conference on Human-Computer Interaction (OzCHI) · doi:10.1145/3726986.3727047 · Cited by 4
“Instead of attributing errors to the user, the conversational agent should be designed to take responsibility for mistakes, ensuring that interactions remain respectful and focused on constructive engagement [12].”
Assistant Robot With Emotion Detection And Display Abilities Survey
Jain, N., Kulshreshtha, V., & Vivek, V. (2022) · International Conference on Advances in Computing, Communication Control and Networking (ICAC3N) · doi:10.1109/icac3n56670.2022.10074162
“Furthermore, future work can be conducted in the fields of error detection and self-repair of errors [14][15][16], as well as the development of arm and limb movement [17][18].”
BackgroundHuman Perception of AI Capabilities at Classifying Perturbed Roadway Signs
Garcia, K. R., Chen, J., Xiao, Y., Mishler, S., Wang, C., & Hu, B. (2025) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2025.3573173
“However, in another context, voice recognition, people lose the willingness to rely on and trust a voice assistant after it fails to correctly recognize a spoken command [43], [44].”
Enhancing Adaptive Human-Agent Teaming Systems with Functional Near-Infrared Spectroscopy
Eloy, L., Doherty, E. J., Spencer, C. A., & Hirshfield, L. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2524490 · Cited by 1
“A large body of work exists specifically using conversational agents to facilitate group discussions and improve participation (Bagmar et al., 2022; Cuadra et al., 2021; Do et al., 2023; Engel et al., 2015; Kim et al., 2020; Tegos et al., 2014; Wang et al., 2017).”
Tonkin, E. L., & Tourte, G. J. L. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-09117-8_10
Namaste Alexa: The Impact of Non‐Native Language Queries on Voice Assistant Usage Intentions
Kaur, J., Agarwal, S., Kaur, S., & Mogaji, E. (2026) · Journal of Consumer Behaviour · doi:10.1002/cb.70108
Relief through digital modalities: evaluating text-based chatbots and voicebots in service failures
Nguyen, M., Arango, L., Zhang, Y., Hartley, N., & Septianto, F. (2026) · European Journal of Marketing · doi:10.1108/ejm-08-2024-0693 · Cited by 2
Agarwal, C., & Krishnaswamy, V. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2639098
Age and generational differences in anthropomorphism and trust in large language models
Cohn, M., Pushkarna, M., Díaz, M., Cooper, J., Olanubi, G. O., Moran, J. M., Mengesha, Z., & Heldreth, C. M. (2026) · Frontiers in Cognition · doi:10.3389/fcogn.2026.1824836
Xiao, Y., & Zhang, H. (2026) · Marketing Intelligence & Planning · doi:10.1108/mip-10-2025-0782
Fahim, M., Syrmoudis, E., & Großklags, J. (2026) · ACM International Conference on Intelligent Virtual Agents (IVA) · doi:10.1145/3806774.3827993
Metadata
- Authors
- Cuadra, A., Li, S., Lee, H., Cho, J., & Ju, W.
- Affiliations
- Cornell Tech (US)
- Tongji University (CN)
- Cornell University (US)
- Venue
- Proceedings of the ACM on Human-Computer Interaction
- Published
- 2021-04-13
- Volume
- 5
- Issue
- CSCW1
- Pages
- 1-24
- ISSN
- 2573-0142 (ISSN-L)
- OpenAlex
- W3159016082
- Cited by
- 52
- References
- 60
- Citations by year
- 2026: 11 · 2025: 10 · 2024: 15 · 2023: 13 · 2022: 3
- FWCI
- 2.74
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Proceedings of the ACM on Human-Computer Interaction (publishedVersion)
- Funders
- Mozilla Foundation
- 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
- voice assistants, conversational repair, self-healing, error correction, overcorrection, undercorrection, Amazon Alexa, voice user interface design
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.
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.