{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:31:10Z","timestamp":1773376270695,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,16]]},"DOI":"10.1145\/3776734.3794426","type":"proceedings-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:05:48Z","timestamp":1773345948000},"page":"412-415","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deployment-Oriented Benchmarking of Open-Source Large Language Models for Social Robots"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0958-4679","authenticated-orcid":false,"given":"Nathan","family":"Pereira","sequence":"first","affiliation":[{"name":"Appalachian State University, Boone, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4292-3404","authenticated-orcid":false,"given":"Yeganeh","family":"Madadi","sequence":"additional","affiliation":[{"name":"Appalachian State University, Boone, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"371","volume-title":"Understanding large-language model (llm)-powered human-robot interaction,\" in Proceedings of the 2024 ACM\/IEEE international conference on human-robot interaction","author":"Kim C. Y.","year":"2024","unstructured":"C. Y. Kim, C. P. Lee, and B. Mutlu, \"Understanding large-language model (llm)-powered human-robot interaction,\" in Proceedings of the 2024 ACM\/IEEE international conference on human-robot interaction, 2024, pp. 371-380."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aat5954"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.3102\/0034654318821286"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jai"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.3390\/app11146522"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1177\/2050157919843961"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1111\/nyas.15007"},{"issue":"254","key":"e_1_3_2_1_9_1","first-page":"1","article-title":"Promptbench: A unifi ed library for evaluation of large language models","volume":"25","author":"Zhu K.","year":"2024","unstructured":"K. Zhu, Q. Zhao, H. Chen, J. Wang, and X. Xie, \"Promptbench: A unifi ed library for evaluation of large language models,\" Journal of Machine Learning Research, vol. 25, no. 254, pp. 1-22, 2024.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_10_1","first-page":"1","article-title":"Comparative benchmarking of the DeepSeek large language model on medical tasks and clinical reasoning","author":"Tordjman M.","year":"2025","unstructured":"M. Tordjman et al., \"Comparative benchmarking of the DeepSeek large language model on medical tasks and clinical reasoning,\" Nature medicine, pp. 1-1, 2025.","journal-title":"Nature medicine"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.3390\/info16050366"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10758-024-09731-8"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1111\/jcal.12872"},{"key":"e_1_3_2_1_15_1","volume-title":"Scaling laws for neural language models,\" arXiv preprint arXiv","author":"Kaplan J.","year":"2001","unstructured":"J. Kaplan et al., \"Scaling laws for neural language models,\" arXiv preprint arXiv: 2001.08361, 2020."},{"key":"e_1_3_2_1_16_1","first-page":"67","volume-title":"What is the best model? application-driven evaluation for large language models,\" in CCF International Conference on Natural Language Processing and Chinese Computing","author":"Lian S.","year":"2024","unstructured":"S. Lian et al., \"What is the best model? application-driven evaluation for large language models,\" in CCF International Conference on Natural Language Processing and Chinese Computing, 2024 : Springer, pp. 67-79."}],"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":"2026-03-12T20:06:35Z","timestamp":1773345995000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3776734.3794426"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":16,"alternative-id":["10.1145\/3776734.3794426","10.1145\/3776734"],"URL":"https:\/\/doi.org\/10.1145\/3776734.3794426","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"}}]}}