{"id":"https://openalex.org/W7135088357","doi":"https://doi.org/10.1145/3776734.3794354","title":"CareEval: Evaluating Large Language Models for Decision-Making in Physical Robot Caregiving","display_name":"CareEval: Evaluating Large Language Models for Decision-Making in Physical Robot Caregiving","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135088357","doi":"https://doi.org/10.1145/3776734.3794354"},"language":null,"primary_location":{"id":"doi:10.1145/3776734.3794354","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776734.3794354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128821625","display_name":"Ziang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziang Liu","raw_affiliation_strings":["Cornell University, Ithaca, USA"],"raw_orcid":"https://orcid.org/0000-0001-6274-0459","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049252282","display_name":"Katherine Dimitropoulou","orcid":"https://orcid.org/0000-0002-1949-0885"},"institutions":[{"id":"https://openalex.org/I45029084","display_name":"City University of Seattle","ror":"https://ror.org/008a9hf75","country_code":"US","type":"education","lineage":["https://openalex.org/I4210086682","https://openalex.org/I45029084"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine Dimitropoulou","raw_affiliation_strings":["Columbia University, New York City, USA"],"raw_orcid":"https://orcid.org/0000-0002-1949-0885","affiliations":[{"raw_affiliation_string":"Columbia University, New York City, USA","institution_ids":["https://openalex.org/I78577930","https://openalex.org/I45029084"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Christy Cheung","orcid":"https://orcid.org/0009-0005-9481-6063"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christy Cheung","raw_affiliation_strings":["Cornell University, Ithaca, USA"],"raw_orcid":"https://orcid.org/0009-0005-9481-6063","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026083794","display_name":"Tapomayukh Bhattacharjee","orcid":"https://orcid.org/0000-0001-9457-5726"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tapomayukh Bhattacharjee","raw_affiliation_strings":["Cornell University, Ithaca, USA"],"raw_orcid":"https://orcid.org/0000-0001-9457-5726","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33059574,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.5055000185966492,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.5055000185966492,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08959999680519104,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.03590000048279762,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3921000063419342},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3449999988079071},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.2953999936580658},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.28769999742507935},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.26750001311302185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5591999888420105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41830000281333923},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3840999901294708},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3495999872684479},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3776734.3794354","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776734.3794354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6896684169769287,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2970482702","https://openalex.org/W2995211792","https://openalex.org/W3083410900","https://openalex.org/W3088056511","https://openalex.org/W3177813494","https://openalex.org/W4221154592","https://openalex.org/W4285195656","https://openalex.org/W4286892945","https://openalex.org/W4287662337","https://openalex.org/W4306808908","https://openalex.org/W4307123345","https://openalex.org/W4312786635","https://openalex.org/W4383097638","https://openalex.org/W4385374425","https://openalex.org/W4396775553","https://openalex.org/W4399153591","https://openalex.org/W4402692877","https://openalex.org/W4403420208","https://openalex.org/W4404330874","https://openalex.org/W4404406987","https://openalex.org/W4405903187","https://openalex.org/W4406658975","https://openalex.org/W4408286179","https://openalex.org/W4409417438","https://openalex.org/W4409962110","https://openalex.org/W4410297676","https://openalex.org/W4414939355","https://openalex.org/W4415068550","https://openalex.org/W4415685811","https://openalex.org/W6891853064","https://openalex.org/W6948369276","https://openalex.org/W7077044503"],"related_works":[],"abstract_inverted_index":{"We":[0,96],"present":[1],"CareEval,":[2],"a":[3,18],"benchmark":[4],"for":[5,55],"evaluating":[6],"the":[7,78,100],"physical":[8,57,94],"caregiving":[9,24,58],"decision-making":[10],"abilities":[11],"of":[12,41,45,99],"Large":[13],"Language":[14],"Models.":[15],"Developed":[16],"with":[17,71],"licensed":[19],"occupational":[20],"therapist":[21],"expert":[22,72],"in":[23,87],"and":[25,67,69,103],"validated":[26],"by":[27],"eight":[28],"clinical":[29],"stakeholders,":[30],"it":[31],"contains":[32],"100":[33],"realistic":[34],"scenarios":[35,102],"spanning":[36],"all":[37,104],"six":[38],"basic":[39],"Activities":[40],"Daily":[42],"Living.":[43],"Instead":[44],"testing":[46],"general":[47],"reasoning,":[48],"CareEval":[49,101],"assesses":[50],"whether":[51],"model":[52,80],"responses":[53],"account":[54],"key":[56],"factors,":[59],"such":[60],"as":[61],"user":[62],"function,":[63],"agency,":[64],"intent,":[65],"communication,":[66],"safety,":[68],"align":[70],"practice.":[73],"Across":[74],"several":[75],"state-of-the-art":[76],"LLMs,":[77],"best":[79],"only":[81],"scores":[82],"53.1%,":[83],"revealing":[84],"substantial":[85],"gaps":[86],"current":[88],"models\u2019":[89],"ability":[90],"to":[91],"reason":[92],"about":[93],"caregiving.":[95],"release":[97],"80":[98],"prompts":[105],"through":[106],"our":[107],"website:":[108],"https://emprise.cs.cornell.edu/care-eval/.":[109]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-13T00:00:00"}