{"id":"https://openalex.org/W4412945320","doi":"https://doi.org/10.18653/v1/2025.acl-long.597","title":"HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devices","display_name":"HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devices","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945320","doi":"https://doi.org/10.18653/v1/2025.acl-long.597"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.597","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.597","pdf_url":"https://aclanthology.org/2025.acl-long.597.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.597.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103037806","display_name":"Silin Li","orcid":"https://orcid.org/0000-0002-4543-1141"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Silin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017544512","display_name":"Y. Jay Guo","orcid":"https://orcid.org/0000-0001-6008-9682"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhang Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056293422","display_name":"JingTao Yao","orcid":"https://orcid.org/0000-0002-7823-4136"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiashu Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103008895","display_name":"Zeming Liu","orcid":"https://orcid.org/0000-0002-3691-8097"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeming Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100386385","display_name":"Haifeng Wang","orcid":"https://orcid.org/0000-0001-5381-1657"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haifeng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1830651,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12230","last_page":"12250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12546","display_name":"Smart Parking Systems Research","score":0.910099983215332,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12546","display_name":"Smart Parking Systems Research","score":0.910099983215332,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5790836215019226},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3993876576423645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5790836215019226},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3993876576423645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.597","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.597","pdf_url":"https://aclanthology.org/2025.acl-long.597.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.597","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.597","pdf_url":"https://aclanthology.org/2025.acl-long.597.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2563629645","display_name":null,"funder_award_id":"U21B2009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323110","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945320.pdf","grobid_xml":"https://content.openalex.org/works/W4412945320.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4,36,72,125],"the":[5,97,107,141,149,162,178],"potential":[6],"to":[7,16],"revolutionize":[8],"smart":[9,41,101,109],"home":[10,32,42,102,110],"assistants":[11],"by":[12],"enhancing":[13],"their":[14],"ability":[15],"accurately":[17,78],"understand":[18],"user":[19,84,89],"needs":[20],"and":[21,60,80,86,95,114,119,169,172],"respond":[22],"appropriately,":[23],"which":[24],"is":[25],"extremely":[26],"beneficial":[27],"for":[28],"building":[29],"a":[30,136],"smarter":[31],"environment.While":[33],"recent":[34],"studies":[35],"explored":[37],"integrating":[38],"LLMs":[39,76,152],"into":[40],"systems,":[43],"they":[44],"primarily":[45],"focus":[46],"on":[47,128],"handling":[48],"straightforward,":[49],"valid":[50,113],"single-device":[51],"operation":[52],"instructions.However,":[53],"real-world":[54],"scenarios":[55],"are":[56,174],"far":[57],"more":[58],"complex":[59],"often":[61],"involve":[62],"users":[63],"issuing":[64],"invalid":[65,115,144],"instructions":[66,85,90,116],"or":[67],"controlling":[68],"multiple":[69,88,120],"devices":[70,121],"simultaneously.These":[71],"two":[73],"main":[74],"challenges:":[75],"must":[77],"identify":[79],"rectify":[81],"errors":[82],"in":[83,122,140,157],"execute":[87],"perfectly.To":[91],"address":[92],"these":[93],"challenges":[94],"advance":[96],"development":[98],"of":[99,143,164],"LLM-based":[100],"assistants,":[103],"we":[104],"introduce":[105],"HomeBench,":[106],"first":[108],"dataset":[111,173],"with":[112,161],"across":[117],"single":[118],"this":[123,158],"paper.We":[124],"experimental":[126],"results":[127],"13":[129],"distinct":[130],"LLMs;":[131],"e.g.,":[132],"GPT-4o":[133],"achieves":[134],"only":[135],"0.0%":[137],"success":[138],"rate":[139],"scenario":[142],"multi-device":[145],"instructions,":[146],"revealing":[147],"that":[148],"existing":[150],"stateof-the-art":[151],"still":[153],"cannot":[154],"perform":[155],"well":[156],"situation":[159],"even":[160],"help":[163],"in-context":[165],"learning,":[166],"retrieval-augmented":[167],"generation,":[168],"fine-tuning.Our":[170],"code":[171],"publicly":[175],"available":[176],"at":[177],"link":[179],"1":[180],".":[181]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
