{"id":"https://openalex.org/W4412944840","doi":"https://doi.org/10.18653/v1/2025.acl-long.992","title":"Error-driven Data-efficient Large Multimodal Model Tuning","display_name":"Error-driven Data-efficient Large Multimodal Model Tuning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944840","doi":"https://doi.org/10.18653/v1/2025.acl-long.992"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.992","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.992","pdf_url":"https://aclanthology.org/2025.acl-long.992.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.992.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011794894","display_name":"Barry Menglong Yao","orcid":"https://orcid.org/0000-0003-1049-7973"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barry Menglong Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055007304","display_name":"Qifan Wang","orcid":"https://orcid.org/0000-0002-5304-7975"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qifan Wang","raw_affiliation_strings":["UC Davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101307306","display_name":"Lifu Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lifu Huang","raw_affiliation_strings":["UC Davis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Davis","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.624,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83285096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"20289","last_page":"20306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.4447999894618988,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.4447999894618988,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.744656503200531},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.45326751470565796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32337865233421326},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.12722238898277283}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.744656503200531},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.45326751470565796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32337865233421326},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.12722238898277283}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.992","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.992","pdf_url":"https://aclanthology.org/2025.acl-long.992.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.992","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.992","pdf_url":"https://aclanthology.org/2025.acl-long.992.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/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944840.pdf","grobid_xml":"https://content.openalex.org/works/W4412944840.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],"Multimodal":[1],"Models":[2],"(LMMs)":[3],"have":[4],"demonstrated":[5],"impressive":[6],"performance":[7,19,166,173],"across":[8,147],"numerous":[9],"academic":[10],"benchmarks.However,":[11],"fine-tuning":[12],"still":[13],"remains":[14],"essential":[15],"to":[16,37,50,55,132,140],"achieve":[17],"satisfactory":[18],"on":[20,78,119,167],"downstream":[21,168],"tasks,":[22,155,169],"while":[23],"the":[24,84,99,103,116,134,141],"task-specific":[25,62],"tuning":[26,46],"samples":[27,124],"are":[28,125],"usually":[29],"not":[30],"readily":[31],"available":[32],"or":[33],"expensive":[34],"and":[35,87,108,137,153,162],"time-consuming":[36],"obtain.To":[38],"address":[39],"this,":[40],"we":[41],"propose":[42],"an":[43,171],"error-driven":[44],"data-efficient":[45],"framework":[47],"that":[48,157],"aims":[49],"efficiently":[51,163],"adapt":[52],"generic":[53,68],"LMMs":[54],"newly":[56],"emerging":[57],"tasks":[58],"without":[59],"requiring":[60],"extensive":[61,145],"training":[63,123,150,159],"samples.In":[64],"our":[65,158],"approach,":[66],"a":[67,72,79,89,95],"LMM,":[69],"acting":[70,93],"as":[71,94],"student":[73,104,135],"model,":[74,92,97],"is":[75],"first":[76],"evaluated":[77],"small":[80],"validation":[81],"set":[82],"of":[83,175],"target":[85,117,142],"task,":[86],"then":[88],"more":[90],"powerful":[91],"teacher":[96],"identifies":[98],"erroneous":[100],"steps":[101,107],"within":[102],"model's":[105],"reasoning":[106],"analyzes":[109],"its":[110],"capability":[111],"gaps":[112],"from":[113,128],"fully":[114],"addressing":[115],"task.Based":[118],"these":[120],"gaps,":[121],"targeted":[122],"further":[126],"retrieved":[127],"existing":[129],"taskagnostic":[130],"datasets":[131],"tune":[133],"model":[136],"tailor":[138],"it":[139],"task.We":[143],"perform":[144],"experiments":[146],"three":[148],"different":[149],"data":[151],"scales":[152],"seven":[154],"demonstrating":[156],"paradigm":[160],"significantly":[161],"improves":[164],"LMM's":[165],"achieving":[170],"average":[172],"boost":[174],"7.01%":[176],"1":[177],".":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}