{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T04:56:34Z","timestamp":1781844994893,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":77,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,11]],"date-time":"2024-03-11T00:00:00Z","timestamp":1710115200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Sheldon B. and Marianne S. Lubar Professorship, an H.I. Romnes Faculty Fellowship, and a National Science Foundation award","award":["1925043"],"award-info":[{"award-number":["1925043"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,11]]},"DOI":"10.1145\/3610977.3634966","type":"proceedings-article","created":{"date-parts":[[2024,3,10]],"date-time":"2024-03-10T00:19:00Z","timestamp":1710029940000},"page":"371-380","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":126,"title":["Understanding Large-Language Model (LLM)-powered Human-Robot Interaction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4195-8317","authenticated-orcid":false,"given":"Callie Y.","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Computer Sciences, University of Wisconsin - Madison, Madison, WI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0991-8072","authenticated-orcid":false,"given":"Christine P.","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computer Sciences, University of Wisconsin - Madison, Madison, WI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9456-1495","authenticated-orcid":false,"given":"Bilge","family":"Mutlu","sequence":"additional","affiliation":[{"name":"Department of Computer Sciences, University of Wisconsin - Madison, Madison, WI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,3,11]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Michael Ahn Anthony Brohan Noah Brown Yevgen Chebotar Omar Cortes Byron David Chelsea Finn Chuyuan Fu Keerthana Gopalakrishnan Karol Hausman et al. 2022. Do as i can not as i say: Grounding language in robotic affordances. arXiv preprint arXiv:2204.01691 (2022)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3029798.3038394"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2008.4600749"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-010-0082-7"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-008-0001--3"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1067860.1067867"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568294.3580040"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","unstructured":"Gestures in human-robot interaction. Ph. D. Dissertation. Humboldt-Universit\u00e4t zu Berlin Mathematisch-Naturwissenschaftliche Fakult\u00e4t. https:\/\/doi.org\/10.18452\/17705","DOI":"10.18452\/17705"},{"key":"e_1_3_2_1_9_1","volume-title":"Social robotics","author":"Breazeal Cynthia","year":"2016","unstructured":"Cynthia Breazeal, Kerstin Dautenhahn, and Takayuki Kanda. 2016. Social robotics. Springer handbook of robotics (2016), 1935--1972."},{"key":"e_1_3_2_1_10_1","unstructured":"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 Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_11_1","volume-title":"Birthe Nesset, Meriam Moujahid, Tanvi Dinkar, et al.","author":"Cherakara Neeraj","year":"2023","unstructured":"Neeraj Cherakara, Finny Varghese, Sheena Shabana, Nivan Nelson, Abhiram Karukayil, Rohith Kulothungan, Mohammed Afil Farhan, Birthe Nesset, Meriam Moujahid, Tanvi Dinkar, et al. 2023. FurChat: An Embodied Conversational Agent using LLMs, Combining Open and Closed-Domain Dialogue with Facial Expressions. arXiv preprint arXiv:2308.15214 (2023)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157798"},{"key":"e_1_3_2_1_13_1","volume-title":"Encyclopedia of critical psychology","author":"Clarke Victoria","year":"1947","unstructured":"Victoria Clarke and Virginia Braun. 2014. Thematic analysis. In Encyclopedia of critical psychology. Springer, 1947--1952."},{"key":"e_1_3_2_1_14_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano Christopher Hesse and John Schulman. 2021. Training Verifiers to Solve Math Word Problems. arxiv: 2110.14168 [cs.LG]"},{"key":"e_1_3_2_1_15_1","volume-title":"Developing and using a codebook for the analysis of interview data: An example from a professional development research project. Field methods","author":"DeCuir-Gunby Jessica T","year":"2011","unstructured":"Jessica T DeCuir-Gunby, Patricia L Marshall, and Allison W McCulloch. 2011. Developing and using a codebook for the analysis of interview data: An example from a professional development research project. Field methods, Vol. 23, 2 (2011), 136--155."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1561\/9781680835472"},{"key":"e_1_3_2_1_17_1","unstructured":"Danny Driess Fei Xia Mehdi S. M. Sajjadi Corey Lynch Aakanksha Chowdhery Brian Ichter Ayzaan Wahid Jonathan Tompson Quan Vuong Tianhe Yu Wenlong Huang Yevgen Chebotar Pierre Sermanet Daniel Duckworth Sergey Levine Vincent Vanhoucke Karol Hausman Marc Toussaint Klaus Greff Andy Zeng Igor Mordatch and Pete Florence. 2023. PaLM-E: An Embodied Multimodal Language Model. arxiv: 2303.03378 [cs.LG]"},{"key":"e_1_3_2_1_18_1","unstructured":"Yingqiang Ge Wenyue Hua Kai Mei Jianchao Ji Juntao Tan Shuyuan Xu Zelong Li and Yongfeng Zhang. 2023. OpenAGI: When LLM Meets Domain Experts. arxiv: 2304.04370 [cs.AI]"},{"key":"e_1_3_2_1_19_1","unstructured":"Google. 2023. Google Cloud Services--Speech to text. \"Accessed = 09--29--2023\"."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2696454.2696495"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2013.04.007"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"2799","author":"Houlsby Neil","year":"2019","unstructured":"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 International 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"},{"key":"e_1_3_2_1_23_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. CoRR","author":"Hu Edward J.","year":"2021","unstructured":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. CoRR , Vol. abs\/2106.09685 (2021). showeprint[arXiv]2106.09685 https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"e_1_3_2_1_24_1","volume-title":"Robotics: Science and Systems","volume":"2","author":"Huang Chien-Ming","year":"2013","unstructured":"Chien-Ming Huang and Bilge Mutlu. 2013. Modeling and Evaluating Narrative Gestures for Humanlike Robots.. In Robotics: Science and Systems, Vol. 2. Citeseer."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","unstructured":"Bahar Irfan Sanna-Mari Kuoppam\u00e4ki and Gabriel Skantze. 2023. Between Reality and Delusion: Challenges of Applying Large Language Models to Companion Robots for Open-Domain Dialogues with Older Adults. https:\/\/doi.org\/10.21203\/rs.3.rs-2884789\/v1","DOI":"10.21203\/rs.3.rs-2884789\/v1"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2018.8525652"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of PRESENCE","volume":"2004","author":"Jung Younbo","year":"2004","unstructured":"Younbo Jung and Kwan Min Lee. 2004. Effects of physical embodiment on social presence of social robots. Proceedings of PRESENCE , Vol. 2004 (2004), 80--87."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568294.3580067"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Krishna Kodur Manizheh Zand Matthew Tognotti Cinthya Jauregui and Maria Kyrarini. 2023. Structured and Unstructured Speech2Action Frameworks for Human-Robot Collaboration: A User Study. (2023).","DOI":"10.36227\/techrxiv.24022452.v1"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1515\/pjbr-2021-0011"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501955"},{"key":"e_1_3_2_1_33_1","unstructured":"Yoon Kyung Lee Yoonwon Jung Gyuyi Kang and Sowon Hahn. 2023. Developing Social Robots with Empathetic Non-Verbal Cues Using Large Language Models. arxiv: 2308.16529 [cs.RO]"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-013-0178-y"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2015.01.001"},{"key":"e_1_3_2_1_36_1","first-page":"1950","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","volume":"35","author":"Liu Haokun","year":"2022","unstructured":"Haokun Liu, Derek Tam, Mohammed Muqeeth, Jay Mohta, Tenghao Huang, Mohit Bansal, and Colin A Raffel. 2022. Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning. Advances in Neural Information Processing Systems , Vol. 35 (2022), 1950--1965.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","volume-title":"Machine Learning in Medical Imaging","author":"Liu Zhengliang","unstructured":"Zhengliang Liu, Aoxiao Zhong, Yiwei Li, Longtao Yang, Chao Ju, Zihao Wu, Chong Ma, Peng Shu, Cheng Chen, Sekeun Kim, Haixing Dai, Lin Zhao, Dajiang Zhu, Jun Liu, Wei Liu, Dinggang Shen, Quanzheng Li, Tianming Liu, and Xiang Li. 2024. Tailoring Large Language Models to\u00a0Radiology: A Preliminary Approach to\u00a0LLM Adaptation for\u00a0a\u00a0Highly Specialized Domain. In Machine Learning in Medical Imaging, Xiaohuan Cao, Xuanang Xu, Islem Rekik, Zhiming Cui, and Xi Ouyang (Eds.). Springer Nature Switzerland, Cham, 464--473."},{"key":"e_1_3_2_1_38_1","volume-title":"Measuring usability with the use questionnaire12. Usability interface","author":"Lund Arnold M","year":"2001","unstructured":"Arnold M Lund. 2001. Measuring usability with the use questionnaire12. Usability interface, Vol. 8, 2 (2001), 3--6."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2018.8525767"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2016.7745234"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025786"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3322276.3322340"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359174"},{"key":"e_1_3_2_1_44_1","volume-title":"Groups: Interaction and performance.","author":"McGrath Joseph Edward","year":"1984","unstructured":"Joseph Edward McGrath. 1984. Groups: Interaction and performance. Vol. 14. Prentice-Hall Englewood Cliffs, NJ."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/1957656.1957786"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2020.101965"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2070719.2070725"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2006.314397"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/1514095.1514109"},{"key":"e_1_3_2_1_50_1","volume-title":"Proceedings of the 15th International Conference on Ubiquitous Computing & Ambient Intelligence (UCAmI","author":"Onorati Teresa","year":"2023","unstructured":"Teresa Onorati, \u00c1lvaro Castro-Gonz\u00e1lez, Javier Cruz del Valle, Paloma D\u00edaz, and Jos\u00e9 Carlos Castillo. 2023. Creating Personalized Verbal Human-Robot Interactions Using LLM with\u00a0the\u00a0Robot Mini. In Proceedings of the 15th International Conference on Ubiquitous Computing & Ambient Intelligence (UCAmI 2023), Jos\u00e9 Bravo and Gabriel Urz\u00e1iz (Eds.). Springer Nature Switzerland, Cham, 148--159."},{"key":"e_1_3_2_1_51_1","unstructured":"Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll L. Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray John Schulman Jacob Hilton Fraser Kelton Luke Miller Maddie Simens Amanda Askell Peter Welinder Paul Christiano Jan Leike and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. arxiv: 2203.02155 [cs.CL]"},{"key":"e_1_3_2_1_52_1","unstructured":"Baolin Peng Michel Galley Pengcheng He Hao Cheng Yujia Xie Yu Hu Qiuyuan Huang Lars Liden Zhou Yu Weizhu Chen and Jianfeng Gao. 2023. Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback. arxiv: 2302.12813 [cs.CL]"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/1228716.1228736"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI53351.2022.9889664"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2019.8673226"},{"key":"e_1_3_2_1_56_1","unstructured":"Aldebaran Robotics. 2023 a. Animated Speech. \"Accessed = 09--29--2023\"."},{"key":"e_1_3_2_1_57_1","unstructured":"Aldebaran Robotics. 2023 b. Audio Device API. \"Accessed = 09--29--2023\"."},{"key":"e_1_3_2_1_58_1","unstructured":"Soft Bank Robotics. 2023 c. Pepper Robot. \"Accessed = 09--29--2023\"."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2015.06.001"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-011-0124-9"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-012-0174-7"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33197-8_12"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/2696454.2696471"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586182.3616623"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"crossref","unstructured":"Jianhao Shen Yichun Yin Lin Li Lifeng Shang Xin Jiang Ming Zhang and Qun Liu. 2021. Generate & Rank: A Multi-task Framework for Math Word Problems. arxiv: 2109.03034 [cs.CL]","DOI":"10.18653\/v1\/2021.findings-emnlp.195"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/1518701.1519021"},{"key":"e_1_3_2_1_68_1","volume-title":"Understanding the capabilities, limitations, and societal impact of large language models. arXiv preprint arXiv:2102.02503","author":"Tamkin Alex","year":"2021","unstructured":"Alex Tamkin, Miles Brundage, Jack Clark, and Deep Ganguli. 2021. Understanding the capabilities, limitations, and societal impact of large language models. arXiv preprint arXiv:2102.02503 (2021)."},{"key":"e_1_3_2_1_69_1","unstructured":"Rohan Taori Ishaan Gulrajani Tianyi Zhang Yann Dubois Xuechen Li Carlos Guestrin Percy Liang and Tatsunori B Hashimoto. 2023. Stanford alpaca: An instruction-following llama model."},{"key":"e_1_3_2_1_70_1","first-page":"20","article-title":"Chatgpt for robotics: Design principles and model abilities","volume":"2","author":"Vemprala Sai","year":"2023","unstructured":"Sai Vemprala, Rogerio Bonatti, Arthur Bucker, and Ashish Kapoor. 2023. Chatgpt for robotics: Design principles and model abilities. Microsoft Auton. Syst. Robot. Res , Vol. 2 (2023), 20.","journal-title":"Microsoft Auton. Syst. Robot. Res"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2006.314404"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2007.4415207"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"crossref","unstructured":"Yizhong Wang Yeganeh Kordi Swaroop Mishra Alisa Liu Noah A. Smith Daniel Khashabi and Hannaneh Hajishirzi. 2023. Self-Instruct: Aligning Language Models with Self-Generated Instructions. arxiv: 2212.10560 [cs.CL]","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2023.2244554"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3282111"},{"key":"e_1_3_2_1_76_1","volume-title":"Proceedings of the 25th Annual Cognitive Science Society. Psychology Press, 1305--1310","author":"Ziemke Tom","year":"2013","unstructured":"Tom Ziemke. 2013. What's that thing called embodiment? In Proceedings of the 25th Annual Cognitive Science Society. Psychology Press, 1305--1310."},{"key":"e_1_3_2_1_77_1","unstructured":"Zoom. 2023. Video Conferencing Platform. \"Accessed = 09--29--2023\". io"}],"event":{"name":"HRI '24: ACM\/IEEE International Conference on Human-Robot Interaction","location":"Boulder CO USA","acronym":"HRI '24","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2024 ACM\/IEEE International Conference on Human-Robot Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610977.3634966","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3610977.3634966","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T16:37:08Z","timestamp":1756399028000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3610977.3634966"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,11]]},"references-count":77,"alternative-id":["10.1145\/3610977.3634966","10.1145\/3610977"],"URL":"https:\/\/doi.org\/10.1145\/3610977.3634966","relation":{},"subject":[],"published":{"date-parts":[[2024,3,11]]},"assertion":[{"value":"2024-03-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}