{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:31:54Z","timestamp":1773376314910,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","funder":[{"name":"National Science Foundation IIS","award":["2132846"],"award-info":[{"award-number":["2132846"]}]},{"name":"CAREER","award":["2238792"],"award-info":[{"award-number":["2238792"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,16]]},"DOI":"10.1145\/3776734.3794354","type":"proceedings-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:05:48Z","timestamp":1773345948000},"page":"57-62","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CareEval: Evaluating Large Language Models for Decision-Making in Physical Robot Caregiving"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6274-0459","authenticated-orcid":false,"given":"Ziang","family":"Liu","sequence":"first","affiliation":[{"name":"Cornell University, Ithaca, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1949-0885","authenticated-orcid":false,"given":"Katherine","family":"Dimitropoulou","sequence":"additional","affiliation":[{"name":"Columbia University, New York City, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9481-6063","authenticated-orcid":false,"given":"Christy","family":"Cheung","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9457-5726","authenticated-orcid":false,"given":"Tapomayukh","family":"Bhattacharjee","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,16]]},"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 Alex Herzog Daniel Ho Jasmine Hsu Julian Ibarz Brian Ichter Alex Irpan Eric Jang Rosario Jauregui Ruano Kyle Jeffrey Sally Jesmonth Nikhil Joshi Ryan Julian Dmitry Kalashnikov Yuheng Kuang Kuang-Huei Lee Sergey Levine Yao Lu Linda Luu Carolina Parada Peter Pastor Jornell Quiambao Kanishka Rao Jarek Rettinghouse Diego Reyes Pierre Sermanet Nicolas Sievers Clayton Tan Alexander Toshev Vincent Vanhoucke Fei Xia Ted Xiao Peng Xu Sichun Xu Mengyuan Yan and Andy Zeng. 2022. Do As I Can and Not As I Say: Grounding Language in Robotic Affordances. In arXiv preprint arXiv:2204.01691."},{"key":"e_1_3_2_1_2_1","unstructured":"Meta AI. 2025. The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation. https:\/\/ai.meta.com\/blog\/llama-4-multimodal-intelligence\/"},{"key":"e_1_3_2_1_3_1","volume-title":"Evaluation of methods used for estimating content validity. Research in social and administrative pharmacy, 15, 2","author":"Almanasreh Enas","year":"2019","unstructured":"Enas Almanasreh, Rebekah Moles, and Timothy F Chen. 2019. Evaluation of methods used for estimating content validity. Research in social and administrative pharmacy, 15, 2 (2019), 214\u2013221."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-323-91888-6.00013-2"},{"key":"e_1_3_2_1_5_1","unstructured":"Anthropic. 2025. Introducing Claude Opus 4.5. https:\/\/www.anthropic.com\/news\/claude-opus-4-5"},{"key":"e_1_3_2_1_6_1","unstructured":"Anthropic. 2026. Advancing Claude in Healthcare and the Life Sciences. https:\/\/www.anthropic.com\/news\/healthcare-life-sciences"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2505.08775"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2024.21700"},{"key":"e_1_3_2_1_9_1","volume-title":"Life Care Planning and Case Management Across the Lifespan","author":"Brown Sarah","unstructured":"Sarah Brown, Amy Thompson, and Sarah Malloy. 2023. The Role of the Occupational Therapist in Life Care Planning. In Life Care Planning and Case Management Across the Lifespan. Routledge, 369\u2013388."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-024-00717-2"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde de Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman Alex Ray Raul Puri Gretchen Krueger Michael Petrov Heidy Khlaaf Girish Sastry Pamela Mishkin Brooke Chan Scott Gray Nick Ryder Mikhail Pavlov Alethea Power Lukasz Kaiser Mohammad Bavarian Clemens Winter Philippe Tillet Felipe Petroski Such Dave Cummings Matthias Plappert Fotios Chantzis Elizabeth Barnes Ariel Herbert-Voss William Hebgen Guss Alex Nichol Alex Paino Nikolas Tezak Jie Tang Igor Babuschkin Suchir Balaji Shantanu Jain William Saunders Christopher Hesse Andrew N. Carr Jan Leike Josh Achiam Vedant Misra Evan Morikawa Alec Radford Matthew Knight Miles Brundage Mira Murati Katie Mayer Peter Welinder Bob McGrew Dario Amodei Sam McCandlish Ilya Sutskever and Wojciech Zaremba. 2021. Evaluating Large Language Models Trained on Code. https:\/\/doi.org\/10.48550\/arXiv.2107.03374 arXiv:2107.03374 [cs] 10.48550\/arXiv.2107.03374","DOI":"10.48550\/arXiv.2107.03374"},{"key":"e_1_3_2_1_12_1","volume-title":"Constructing validity: New developments in creating objective measuring instruments.. Psychological assessment, 31, 12","author":"Clark Lee Anna","year":"2019","unstructured":"Lee Anna Clark and David Watson. 2019. Constructing validity: New developments in creating objective measuring instruments.. Psychological assessment, 31, 12 (2019), 1412."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","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. https:\/\/doi.org\/10.48550\/arXiv.2110.14168 arXiv:2110.14168 [cs] 10.48550\/arXiv.2110.14168","DOI":"10.48550\/arXiv.2110.14168"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"Gheorghe Comanici Eric Bieber Mike Schaekermann Ice Pasupat Noveen Sachdeva et al. 2025. Gemini 2.5: Pushing the Frontier with Advanced Reasoning Multimodality Long Context and Next Generation Agentic Capabilities. https:\/\/doi.org\/10.48550\/arXiv.2507.06261 arXiv:2507.06261 [cs] 10.48550\/arXiv.2507.06261","DOI":"10.48550\/arXiv.2507.06261"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"DeepSeek-AI Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu et al. 2025. DeepSeek-V3 Technical Report. https:\/\/doi.org\/10.48550\/arXiv.2412.19437 arXiv:2412.19437 [cs] 10.48550\/arXiv.2412.19437","DOI":"10.48550\/arXiv.2412.19437"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3758871.3758891"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.4324\/9781003525295-8"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2009.11462"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","unstructured":"Dan Hendrycks Collin Burns Steven Basart Andy Zou Mantas Mazeika Dawn Song and Jacob Steinhardt. 2021. Measuring Massive Multitask Language Understanding. https:\/\/doi.org\/10.48550\/arXiv.2009.03300 arXiv:2009.03300 [cs] 10.48550\/arXiv.2009.03300","DOI":"10.48550\/arXiv.2009.03300"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1310\/sci2504-290"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"Di Jin Eileen Pan Nassim Oufattole Wei-Hung Weng Hanyi Fang and Peter Szolovits. 2020. What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams. https:\/\/doi.org\/10.48550\/arXiv.2009.13081 arXiv:2009.13081 [cs] 10.48550\/arXiv.2009.13081","DOI":"10.48550\/arXiv.2009.13081"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1259"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2411.08123"},{"key":"e_1_3_2_1_24_1","unstructured":"Suzanne Lane Mark R Raymond Thomas M Haladyna et al. 2016. Handbook of test development. 2 Routledge New York NY."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.medp.2025.100084"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Jacky Liang Wenlong Huang Fei Xia Peng Xu Karol Hausman Brian Ichter Pete Florence and Andy Zeng. 2022. Code as Policies: Language Model Programs for Embodied Control. In arXiv preprint arXiv:2209.07753.","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","unstructured":"Stephanie Lin Jacob Hilton and Owain Evans. 2022. TruthfulQA: Measuring How Models Mimic Human Falsehoods. https:\/\/doi.org\/10.48550\/arXiv.2109.07958 arXiv:2109.07958 [cs] 10.48550\/arXiv.2109.07958","DOI":"10.48550\/arXiv.2109.07958"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI61500.2025.10974054"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981936"},{"key":"e_1_3_2_1_30_1","unstructured":"OpenAI. 2025. GPT-5.1: A smarter more conversational ChatGPT. https:\/\/openai.com\/index\/gpt-5-1\/"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","unstructured":"OpenAI Sandhini Agarwal Lama Ahmad Jason Ai Sam Altman Andy Applebaum et al. 2025. gpt-oss-120b & gpt-oss-20b Model Card. https:\/\/doi.org\/10.48550\/arXiv.2508.10925 arXiv:2508.10925 [cs] 10.48550\/arXiv.2508.10925","DOI":"10.48550\/arXiv.2508.10925"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","unstructured":"OpenAI Aaron Hurst Adam Lerer Adam P. Goucher Adam Perelman Aditya Ramesh et al. 2024. GPT-4o System Card. https:\/\/doi.org\/10.48550\/arXiv.2410.21276 arXiv:2410.21276 [cs] 10.48550\/arXiv.2410.21276","DOI":"10.48550\/arXiv.2410.21276"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.14371"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.2196\/54633"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.2196\/70703"},{"key":"e_1_3_2_1_36_1","unstructured":"Andrea Spoto Massimo Nucci Elena Prunetti and Michele Vicovaro. 2023. Improving content validity evaluation of assessment instruments through formal content validity analysis.. Psychological methods."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.09261"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","unstructured":"Kimi Team Yifan Bai Yiping Bao Guanduo Chen Jiahao Chen Ningxin Chen et al. 2025. Kimi K2: Open Agentic Intelligence. https:\/\/doi.org\/10.48550\/arXiv.2507.20534 arXiv:2507.20534 [cs] 10.48550\/arXiv.2507.20534","DOI":"10.48550\/arXiv.2507.20534"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare13060603"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10921-0"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2506.11376"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang et al. 2025. Qwen3 Technical Report. https:\/\/doi.org\/10.48550\/arXiv.2505.09388 arXiv:2505.09388 [cs] 10.48550\/arXiv.2505.09388","DOI":"10.48550\/arXiv.2505.09388"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","unstructured":"Andy Zou Zifan Wang Nicholas Carlini Milad Nasr J. Zico Kolter and Matt Fredrikson. 2023. Universal and Transferable Adversarial Attacks on Aligned Language Models. https:\/\/doi.org\/10.48550\/arXiv.2307.15043 arXiv:2307.15043 [cs] 10.48550\/arXiv.2307.15043","DOI":"10.48550\/arXiv.2307.15043"}],"event":{"name":"HRI '26: 21st ACM\/IEEE International Conference on Human-Robot Interaction","location":"Edinburgh Scotland UK","acronym":"HRI '26","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction","IEEE RAS"]},"container-title":["Companion Proceedings of the 21st ACM\/IEEE International Conference on Human-Robot Interaction"],"original-title":[],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:09:29Z","timestamp":1773346169000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3776734.3794354"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":43,"alternative-id":["10.1145\/3776734.3794354","10.1145\/3776734"],"URL":"https:\/\/doi.org\/10.1145\/3776734.3794354","relation":{},"subject":[],"published":{"date-parts":[[2026,3,16]]},"assertion":[{"value":"2026-03-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}