User Interaction Patterns and Breakdowns in Conversing with LLM-Powered Voice Assistants
Open accessThe claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Large language models have shown enhanced conversational capabilities, yielding robust and fluid interactions with users.
“LLMs, on the other hand, have shown enhanced conversational capabilities, yielding robust and fluid interactions with users [9, 37].”
From Situated Understanding of Errors in Older Adults' Interactions with Voice Assistants: A Month-Long, In-Home Study (2026) · cites this paper as [37]
The Conclusion (p. 24) says LLMs are better than traditional voice assistants at understanding context and handling breakdowns, and reports that ChatGPT absorbed 81% of intent-recognition failures. But it describes more fluid interactions as a goal; the Abstract (p. 1) likewise calls resilient and fluid interactions a potential benefit, rather than an established result. (LLM, conf=0.86)
Experimental — accuracy not yet measuredLarge language models have shown potential in absorbing various speech recognition errors.
“LLMs have also shown potential in absorbing various speech recognition errors [37].”
From Situated Understanding of Errors in Older Adults' Interactions with Voice Assistants: A Month-Long, In-Home Study (2026) · cites this paper as [37]
Previous research indicates that LLMs can potentially mitigate speech recognition errors by absorbing incomplete and incorrect inputs or initiating proactive recovery sequences.
“However, previous research indicates that LLMs can potentially mitigate such errors by absorbing incomplete and incorrect inputs or initiating proactive recovery sequences to prevent conversational breakdowns [37].”
From Situated Understanding of Errors in Older Adults' Interactions with Voice Assistants: A Month-Long, In-Home Study (2026) · cites this paper as [37]
Integrating LLMs into VAs could achieve better contextual understanding and conversation history.
“Integrating LLMs into VAs could achieve this, as LLM-powered VAs have shown to improve natural language understanding, maintain context, and facilitate smoother multi-turn interactions [37].”
From Situated Understanding of Errors in Older Adults' Interactions with Voice Assistants: A Month-Long, In-Home Study (2026) · cites this paper as [37]
LLM-powered VAs have been shown to improve natural language understanding, maintain context, and facilitate smoother multi-turn interactions.
“LLM-powered VAs have shown to improve natural language understanding, maintain context, and facilitate smoother multi-turn interactions [37].”
From Situated Understanding of Errors in Older Adults' Interactions with Voice Assistants: A Month-Long, In-Home Study (2026) · cites this paper as [37]
LLM integration presents a more effective approach to deciphering user intent.
“As such, LLM integration presents a more effective approach to deciphering user intent [37].”
From Situated Understanding of Errors in Older Adults' Interactions with Voice Assistants: A Month-Long, In-Home Study (2026) · cites this paper as [37]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Ayers, J. W., Poliak, A., Dredze, M., Leas, E. C., Zhu, Z., Kelley, J. B., Faix, D. J., Goodman, A. M., Longhurst, C. A., Hogarth, M., et al. (2023) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2023.1838 · Cited by 2,613 · see citing works
Using uh and um in spontaneous speaking
Clark, H. (2002) · Cognition · doi:10.1016/s0010-0277(02)00017-3 · Cited by 1,235 · see citing works
Voice Interfaces in Everyday Life
Porcheron, M., Fischer, J. E., Reeves, S., & Sharples, S. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174214 · Cited by 717 · see citing works
Intelligent systems in tourism
Gretzel, U. (2011) · Annals of Tourism Research · doi:10.1016/j.annals.2011.04.014 · Cited by 468 · see citing works
López, G., Quesada, L., & Guerrero, L. A. (2018) · Advances in Intelligent Systems and Computing · doi:10.1007/978-3-319-60366-7_23 · Cited by 277 · see citing works
Chatbots, Humbots, and the Quest for Artificial General Intelligence
Grudin, J., & Jacques, R. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300439 · Cited by 275 · see citing works
Co-Writing with Opinionated Language Models Affects Users’ Views
Jakesch, M., Bhat, A., Buschek, D., Zalmanson, L., & Naaman, M. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581196 · Cited by 265 · see citing works
Resilient Chatbots: Repair Strategy Preferences for Conversational Breakdowns
Ashktorab, Z., Jain, M., Liao, Q. V., & Weisz, J. D. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300484 · Cited by 224 · see citing works
Patterns for How Users Overcome Obstacles in Voice User Interfaces
Myers, C., Furqan, A., Nebolsky, J., Caro, K., & Zhu, J. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3173580 · Cited by 213 · see citing works
Kim, S., & Choudhury, A. (2021) · Computers in Human Behavior · doi:10.1016/j.chb.2021.106914 · Cited by 200 · see citing works
Jo, E., Epstein, D. A., Jung, H., & Kim, Y.-H. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581503 · Cited by 174 · see citing works
Krämer, N. C., von der Pütten, A., & Eimler, S. (2012) · Studies in Computational Intelligence · doi:10.1007/978-3-642-25691-2_9 · Cited by 135 · see citing works
Conversational UX Design: A Practitioner's Guide to the Natural Conversation Framework
Research-Almaden, I., Moore, R. J., Arar, R., & Research-Almaden, I. (2019) · doi:10.1145/3304087 · Cited by 118 · see citing works
Liao, Q. V., Mas-ud Hussain, M., Chandar, P., Davis, M., Khazaeni, Y., Crasso, M. P., Wang, D., Muller, M., Shami, N. S., & Geyer, W. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3173577 · Cited by 116 · see citing works
Self-citationMapping Perceptions of Humanness in Intelligent Personal Assistant Interaction
Doyle, P. R., Edwards, J., Dumbleton, O., Clark, L., & Cowan, B. R. (2019) · Proceedings of the 21st International Conference on Human-Computer Interaction with Mobile Devices and Services · doi:10.1145/3338286.3340116 · Cited by 100 · see citing works
Harrington, C. N., Garg, R., Woodward, A., & Williams, D. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3501995 · Cited by 98 · see citing works
Human-Computer Interaction: The Agency Perspective
(2012) · Studies in Computational Intelligence · doi:10.1007/978-3-642-25691-2 · Cited by 72 · see citing works
Learning gain differences between ChatGPT and human tutor generated algebra hints
Pardos, Z. A., & Bhandari, S. (2023) · arXiv · doi:10.48550/arxiv.2302.06871 · Cited by 70 · see citing works
Arnold, A., Kolody, S., Comeau, A., & Miguel Cruz, A. (2024) · Disability and Rehabilitation: Assistive Technology · doi:10.1080/17483107.2022.2065369 · Cited by 59 · see citing works
My Bad! Repairing Intelligent Voice Assistant Errors Improves Interaction
Cuadra, A., Li, S., Lee, H., Cho, J., & Ju, W. (2021) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3449101 · Cited by 52 · see citing works
Owning Mistakes Sincerely: Strategies for Mitigating AI Errors
Mahmood, A., Fung, J. W., Won, I., & Huang, C.-M. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3517565 · Cited by 52 · see citing works
Self-citationThe Role of Conversational Grounding in Supporting Symbiosis Between People and Digital Assistants
Cho, J., & Rader, E. (2020) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3392838 · Cited by 49 · see citing works
ChatGPT in Healthcare: Exploring AI Chatbot for Spontaneous Word Retrieval in Aphasia
Purohit, A. K., Upadhyaya, A., & Holzer, A. (2023) · Computer Supported Cooperative Work and Social Computing · doi:10.1145/3584931.3606993 · Cited by 38 · see citing works
Zhong, R., & Ma, M. (2022) · BMC Geriatrics · doi:10.1186/s12877-022-03428-2 · Cited by 36 · see citing works
Flagged first, then by citations
Research works printed but not linked: 17
- Balakesava Reddy, P., Ramasubbareddy, S., and Govinda, K. (2022). Ai-based medical voice assistant during covid-19. In Innovations in Computer Science and Engineering: Proceedings of the Ninth ICICSE, 2021 , pages 119-126. Springer.
- Baldauf, M., Fröehlich, P., and Endl, R. (2020). Trust me, i'ma doctor-user perceptions of ai-driven apps for mobile health diagnosis. In Proceedings of the 19th International Conference on Mobile and Ubiquitous Multimedia , pages 167-178.
- Benner, D., Elshan, E., Schöbel, S., and Janson, A. (2021). What do you mean? a review on recovery strategies to overcome conversational breakdowns of conversational agents. In International Conference on Information Systems (ICIS) .
- Bickmore, T. W., Trinh, H., Olafsson, S., O'Leary, T. K., Asadi, R., Rickles, N. M., and Cruz, R. (2018). Patient and consumer safety risks when using conversational assistants for medical information: an observational study of siri, alexa, and google assistant. Journal of medical Internet research , 20(9):e11510.
- Brewer, R. N. (2022). 'if alexa knew the state i was in, it would cry': Older adults' perspectives of voice assistants for health. In CHI Conference on Human Factors in Computing Systems Extended Abstracts , pages 1-8.
- Cascella, M., Montomoli, J., Bellini, V., and Bignami, E. (2023). Evaluating the feasibility of chatgpt in healthcare: an analysis of multiple clinical and research scenarios. Journal of Medical Systems , 47(1):33.
- Bulchand-Gidumal, J. (2022). Impact of artificial intelligence in travel, tourism, and hospitality. In Handbook of e-Tourism , pages 1943-1962. Springer.
- Chan, S., Li, J., Yao, B., Mahmood, A., Huang, C.-M., Jimison, H., Mynatt, E. D., and Wang, D. (2023). " mango mango, how to let the lettuce dry without a spinner?': Exploring user perceptions of using an llm-based conversational assistant toward cooking partner. arXiv preprint arXiv:2310.05853 . · arXiv
- Cho, M., Lee, S.-s., and Lee, K.-P. (2019). Once a kind friend is now a thing: Understanding how conversational agents at home are forgotten. In Proceedings of the 2019 on Designing Interactive Systems Conference , pages 1557-1569.
- Clark, L., Pantidi, N., Cooney, O., Doyle, P., Garaialde, D., Edwards, J., Spillane, B., Gilmartin, E., Murad, C., Munteanu, C., Wade, V., and Cowan, B. R. (2019). What makes a good conversation? challenges in designing truly conversational agents. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems , CHI '19, page 1-12, New York, NY, USA. Association for Computing Machinery.
- Coupland, J., Coupland, N., and Robinson, J. D. (1992). 'how are you?': Negotiating phatic communion1. Language in society , 21(2):207-230.
- de Medeiros, L. F., Junior, A. K., and Moser, A. (2019). A cognitive assistant that uses small talk in tutoring conversation. International Journal of Emerging Technologies in Learning (Online) , 14(11):138.
- Do, H. J., Yang, S. H., Choi, B.-G., Fu, W. T., and Bailey, B. P. (2021). Do you have time for a quick chat? designing a conversational interface for sexual harassment prevention training. In 26th International Conference on Intelligent User Interfaces , IUI '21, page 542-552, New York, NY, USA. Association for Computing Machinery.
- Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 . · arXiv
- Dong, X. L., Moon, S., Xu, Y. E., Malik, K., and Yu, Z. (2023). Towards next-generation intelligent assistants leveraging llm techniques. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining , KDD '23, page 5792-5793, New York, NY, USA. Association for Computing Machinery.
- Doyle, P. R., Gessinger, I., Edwards, J., Clark, L., Dumbleton, O., Garaialde, D., Rough, D., Bleakley, A., Branigan, H. P., and Cowan, B. R. (2023). The partner modelling questionnaire: A validated self-report measure of perceptions toward machines as dialogue partners. arXiv preprint arXiv:2308.07164 . · arXiv
- Dubberly, H. and Pangaro, P. (2009). What is conversation? how can we design for effective conversation. Interactions Magazine , 16(4):22-28. Fox Tree, J. E. (2001). Listeners' uses of um and uh in speech comprehension. Memory & cognition , 29:320-326.
Cited by
Sorted by citations
Mahmood, A., Wang, J., & Huang, C.-M. (2026) · ACM Transactions on Accessible Computing · doi:10.1145/3796236 · Cited by 6 · see citing works
“This mental model contrasts sharply with that of younger adults in our previous work [11, 47, 48], who more readily understood the integration of LLMs and adapted their interactions accordingly.”
InfluentialSelf-citation
- Authors
- Mahmood, A., Wang, J., Yao, B., Wang, D., & Huang, C.-M.
- Affiliations
- Johns Hopkins University (US)
- Northeastern University (US)
- Corresponding author
- Mahmood, Amama
- Venue
- International Journal of Human-Computer Studies
- Publisher
- Elsevier BV
- Published
- 2025-01
- Volume
- 195
- Pages
- 103406
- ISSN
- 1071-5819 (ISSN-L)
- OpenAlex
- W4404769982
- Cited by
- 51
- References
- 24
- Citations by year
- 2026: 25 · 2025: 23 · 2024: 2 · 2023: 1
- FWCI
- 7.41
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
- www.elsevier.com/legal/tdmrep-license (tdm)
- www.elsevier.com/open-access/userlicense/1.0/ (am, 336 d)
- doi.org/10.15223/policy-017 (stm-asf)
- doi.org/10.15223/policy-037 (stm-asf)
- doi.org/10.15223/policy-012 (stm-asf)
- doi.org/10.15223/policy-029 (stm-asf)
- doi.org/10.15223/policy-004 (stm-asf)
- Locations
- International Journal of Human-Computer Studies (acceptedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by-nc-sa)
- arXiv (Cornell University)
- Funders
- Johns Hopkins University
- National Science Foundation (1840088)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Artificial Intelligence › AI in Service Interactions
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Keywords
- voice assistants, large language models, user interaction patterns, conversational breakdown, intent classification, ChatGPT, creative planning, conversational AI
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
