{"id":"https://openalex.org/W7138455729","doi":"https://doi.org/10.1609/aaai.v40i30.39757","title":"Learning from Reasoning Failures via Synthetic Data Generation","display_name":"Learning from Reasoning Failures via Synthetic Data Generation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138455729","doi":"https://doi.org/10.1609/aaai.v40i30.39757"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i30.39757","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i30.39757","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39757/43718","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39757/43718","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081879623","display_name":"Gabriela Ben Melech Stan","orcid":"https://orcid.org/0000-0001-6893-6647"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gabriela Ben Melech Stan","raw_affiliation_strings":["Intel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129744440","display_name":"Estelle Aflalo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Estelle Aflalo","raw_affiliation_strings":["Intel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129747626","display_name":"Avinash Madasu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Avinash Madasu","raw_affiliation_strings":["Intel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087898808","display_name":"Vasudev Lal","orcid":"https://orcid.org/0000-0002-5907-9898"},"institutions":[{"id":"https://openalex.org/I1342911587","display_name":"Oracle (United States)","ror":"https://ror.org/006c77m33","country_code":"US","type":"company","lineage":["https://openalex.org/I1342911587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vasudev Lal","raw_affiliation_strings":["Oracle"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oracle","institution_ids":["https://openalex.org/I1342911587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129671032","display_name":"Phillip Howard","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Phillip Howard","raw_affiliation_strings":["Thoughtworks"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Thoughtworks","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"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":0.74358974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"30","first_page":"25608","last_page":"25616"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7577999830245972,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7577999830245972,"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/T10028","display_name":"Topic Modeling","score":0.08959999680519104,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.04450000077486038,"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/synthetic-data","display_name":"Synthetic data","score":0.6669999957084656},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.41200000047683716},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4023999869823456},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.33489999175071716},{"id":"https://openalex.org/keywords/data-type","display_name":"Data type","score":0.32359999418258667},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3043000102043152}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7095999717712402},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6675999760627747},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6669999957084656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6401000022888184},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3043000102043152},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27970001101493835},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.2702000141143799},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26100000739097595}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i30.39757","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i30.39757","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39757/43718","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/39757","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/39757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i30.39757","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i30.39757","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39757/43718","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138455729.pdf","grobid_xml":"https://content.openalex.org/works/W7138455729.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Training":[0],"models":[1,27,135,206],"on":[2,198,208,220],"synthetic":[3,61,116,210,234],"data":[4,38,62,117,211,235],"has":[5],"emerged":[6],"as":[7],"an":[8,126,221],"increasingly":[9],"important":[10],"strategy":[11],"for":[12,24,51,115,192],"improving":[13,193],"the":[14,31,60,68,78,97,123,155,194,215,229],"performance":[15,195,216],"of":[16,34,46,71,99,125,196,217,224,232],"generative":[17],"AI.":[18],"This":[19],"approach":[20,114,184],"is":[21,120],"particularly":[22],"helpful":[23],"large":[25,53,173],"multimodal":[26,54,174],"(LMMs)":[28],"due":[29],"to":[30,40,63,96,136,153,166,237],"relative":[32],"scarcity":[33],"high-quality":[35],"paired":[36],"image-text":[37],"compared":[39],"language-only":[41],"data.":[42],"While":[43],"a":[44,87,112,142,172],"variety":[45],"methods":[47],"have":[48,103],"been":[49],"proposed":[50],"generating":[52,233],"datasets,":[55],"they":[56,102],"do":[57],"not":[58],"tailor":[59],"address":[64],"specific":[65,238],"deficiencies":[66],"in":[67,86,122,242],"reasoning":[69,100,129,156,239],"abilities":[70],"LMMs":[72,197,218],"which":[73,119,149,161],"will":[74],"be":[75,151],"trained":[76,207,219],"with":[77],"generated":[79],"dataset.":[80],"In":[81],"contrast,":[82],"humans":[83],"often":[84],"learn":[85],"more":[88],"efficient":[89],"manner":[90],"by":[91,107,141],"seeking":[92],"out":[93],"examples":[94,148,181],"related":[95],"types":[98],"where":[101],"failed":[104],"previously.":[105],"Inspired":[106],"this":[108],"observation,":[109],"we":[110],"propose":[111,146],"new":[113,147],"generation":[118],"grounded":[121],"analysis":[124],"existing":[127],"LMM's":[128],"failures.":[130],"Our":[131,202],"methodology":[132],"leverages":[133],"frontier":[134],"automatically":[137],"analyze":[138],"errors":[139],"produced":[140],"weaker":[143],"LMM":[144],"and":[145,185],"can":[150,212],"used":[152],"correct":[154],"failure":[157,240],"via":[158],"additional":[159,225],"training,":[160],"are":[162],"then":[163],"further":[164],"filtered":[165],"ensure":[167],"high":[168,230],"quality.":[169],"We":[170],"generate":[171],"instruction":[175],"tuning":[176],"dataset":[177],"containing":[178],"over":[179],"553k":[180],"using":[182],"our":[183,209],"conduct":[186],"extensive":[187],"experiments":[188],"demonstrating":[189,228],"its":[190],"utility":[191],"multiple":[199],"downstream":[200],"tasks.":[201],"results":[203],"show":[204],"that":[205],"even":[213],"exceed":[214],"equivalent":[222],"amount":[223],"real":[226],"data,":[227],"value":[231],"targeted":[236],"modes":[241],"LMMs.":[243]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}