{"id":"https://openalex.org/W7140109691","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.159","title":"MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extraction","display_name":"MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extraction","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140109691","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.159"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.159","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.159","pdf_url":"https://aclanthology.org/2026.findings-eacl.159.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.159.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130363099","display_name":"Wei-Chieh Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Chieh Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089085275","display_name":"Cornelia Caragea","orcid":"https://orcid.org/0000-0002-5664-2163"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cornelia Caragea","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3035","last_page":"3053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.10970000177621841,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.10970000177621841,"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"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.09489999711513519,"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"}},{"id":"https://openalex.org/T10656","display_name":"Child and Animal Learning Development","score":0.062199998646974564,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4691999852657318},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.2897000014781952},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.2784000039100647},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.2712000012397766},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.24799999594688416}],"concepts":[{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45899999141693115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.42239999771118164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4075999855995178},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2955000102519989},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24799999594688416},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.24779999256134033}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.159","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.159","pdf_url":"https://aclanthology.org/2026.findings-eacl.159.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.159","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.159","pdf_url":"https://aclanthology.org/2026.findings-eacl.159.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"},{"id":"https://openalex.org/F4320332697","display_name":"University of Illinois at Chicago","ror":"https://ror.org/02mpq6x41"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140109691.pdf","grobid_xml":"https://content.openalex.org/works/W7140109691.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Implicit":[0],"Attribute":[1],"Value":[2],"Extraction":[3],"(AVE)":[4],"is":[5],"essential":[6],"for":[7,96,141],"accurately":[8],"representing":[9],"products":[10],"in":[11,22,41,144],"e-commerce,":[12],"as":[13],"it":[14],"infers":[15],"latent":[16],"attributes":[17,97],"from":[18],"multimodal":[19,23,145],"data.Despite":[20],"advances":[21],"large":[24],"language":[25],"models":[26],"(MLLMs),":[27],"implicit":[28,142],"AVE":[29,143],"remains":[30],"challenging":[31],"due":[32],"to":[33,58,129],"the":[34,81,123,131],"complexity":[35],"of":[36,64,90,125,133],"multidimensional":[37],"data":[38],"and":[39,69,78,113,136],"gaps":[40],"vision-text":[42],"understanding.In":[43],"this":[44],"work,":[45],"we":[46],"introduce":[47],"MADIAVE,":[48],"a":[49,62,87,138],"multi-agent":[50,126],"debate":[51,65,91,105,116,127],"framework":[52],"that":[53,85],"employs":[54],"multiple":[55],"MLLM":[56,111],"agents":[57,67],"iteratively":[59],"refine":[60],"inferences.Through":[61],"series":[63],"rounds,":[66],"verify":[68],"update":[70],"each":[71],"other's":[72],"responses,":[73],"thereby":[74],"improving":[75],"inference":[76],"performance":[77],"robustness.Experiments":[79],"on":[80],"ImplicitAVE":[82],"dataset":[83],"demonstrate":[84],"even":[86],"few":[88],"rounds":[89,117],"significantly":[92],"boost":[93],"accuracy,":[94],"especially":[95],"with":[98],"initially":[99],"low":[100],"performance.We":[101],"systematically":[102],"evaluate":[103],"various":[104],"configurations,":[106],"including":[107],"identical":[108],"or":[109],"different":[110],"agents,":[112],"analyze":[114],"how":[115],"affect":[118],"convergence":[119],"dynamics.Our":[120],"findings":[121],"highlight":[122],"potential":[124],"strategies":[128],"address":[130],"limitations":[132],"single-agent":[134],"approaches":[135],"offer":[137],"scalable":[139],"solution":[140],"e-commerce.":[146]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-24T00:00:00"}