Understanding Large-Language Model (LLM)-powered Human-Robot Interaction
Open accessAbstract
Large-language models (LLMs) hold significant promise in improving human-robot interaction, offering advanced conversational skills and versatility in managing diverse, open-ended user requests in various tasks and domains. Despite the potential to transform human-robot interaction, very little is known about the distinctive design requirements for utilizing LLMs in robots, which may differ from text and voice interaction and vary by task and context. To better understand these requirements, we conducted a user study (n = 32) comparing an LLM-powered social robot against text- and voice-based agents, analyzing task-based requirements in conversational tasks, including choose, generate, execute, and negotiate. Our findings show that LLM-powered robots elevate expectations for sophisticated non-verbal cues and excel in connection-building and deliberation, but fall short in logical communication and may induce anxiety. We provide design implications both for robots integrating LLMs and for fine-tuning LLMs for use with robots.
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.
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?
Social robots can facilitate rich interactions that support children's cognitive and emotional development in the physical world.
“and that social robots can facilitate rich interactions that support children's cognitive and emotional development in the physical world [2, 34, 42, 44, 47].”
From SET-PAiREd: Designing for Parental Involvement in Learning with an AI-Assisted Educational Robot (2025) · cites this paper as [42]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 75 · Cited by 162
Research works printed but not linked: 5
- Cynthia Breazeal, Kerstin Dautenhahn, and Takayuki Kanda. 2016. Social robotics. Springer handbook of robotics (2016), 1935-1972.
- Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877-1901.
- Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-Efficient Transfer Learning for NLP. In Proceedings of the 36th Interna- tional Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 2790-2799. https://proceedings.mlr.press/v97/houlsby19a.html
- Younbo Jung and Kwan Min Lee. 2004. Effects of physical embodiment on social presence of social robots. Proceedings of PRESENCE 2004 (2004), 80-87.
- Arnold M Lund. 2001. Measuring usability with the use questionnaire12. Usability interface 8, 2 (2001), 3-6.
- Authors
- Kim, C. Y., Lee, C. P., & Mutlu, B.
- Affiliations
- University of Wisconsin–Madison (US)
- Venue
- Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction
- Publisher
- ACM
- Published
- 2024-03-11
- Pages
- 371-380
- OpenAlex
- W4390722831
- Cited by
- 162
- References
- 75
- Citations by year
- 2026: 65 · 2025: 63 · 2024: 34
- FWCI
- 108.62
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM/IEEE International Conference on Human-Robot Interaction (HRI) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Sheldon B. and Marianne S. Lubar Professorship, an H.I. Romnes Faculty Fellowship, and a National Science Foundation award (1925043)
- Topics
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Artificial Intelligence › AI in Service Interactions
- Keywords
- large language models, human-robot interaction, social robots, chatbots, text-based interaction, voice interaction, nonverbal cues, negotiation, user expectations, anxiety, LLM fine-tuning
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
