{"id":"https://openalex.org/W7137917254","doi":"https://doi.org/10.1609/aaai.v40i38.40477","title":"Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data","display_name":"Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137917254","doi":"https://doi.org/10.1609/aaai.v40i38.40477"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i38.40477","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40477","pdf_url":null,"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://doi.org/10.1609/aaai.v40i38.40477","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129659365","display_name":"Jiacheng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiacheng Liu","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129739684","display_name":"Mayi Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mayi Xu","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099166967","display_name":"Qiankun Pi","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiankun Pi","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625299","display_name":"Wenli Li","orcid":"https://orcid.org/0000-0001-8711-5094"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenli Li","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129645920","display_name":"Ming Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Zhong","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129647059","display_name":"Yuanyuan Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Zhu","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129712178","display_name":"Mengchi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengchi Liu","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129730309","display_name":"Tieyun Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tieyun Qian","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"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":0.1291548,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"38","first_page":"32060","last_page":"32068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3093999922275543,"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/T10028","display_name":"Topic Modeling","score":0.3093999922275543,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.20080000162124634,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.06620000302791595,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/intervention","display_name":"Intervention (counseling)","score":0.4867999851703644},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4535999894142151},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4480000138282776},{"id":"https://openalex.org/keywords/psychological-intervention","display_name":"Psychological intervention","score":0.42879998683929443},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.3521000146865845},{"id":"https://openalex.org/keywords/empirical-evidence","display_name":"Empirical evidence","score":0.33880001306533813},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.33379998803138733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5961999893188477},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5688999891281128},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4480000138282776},{"id":"https://openalex.org/C27415008","wikidata":"https://www.wikidata.org/wiki/Q7256382","display_name":"Psychological intervention","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3792000114917755},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.36059999465942383},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C87868495","wikidata":"https://www.wikidata.org/wiki/Q750843","display_name":"Information processing","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C136206449","wikidata":"https://www.wikidata.org/wiki/Q3556841","display_name":"Reporting bias","level":3,"score":0.29739999771118164},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C2780439572","wikidata":"https://www.wikidata.org/wiki/Q919364","display_name":"Publication bias","level":3,"score":0.2833999991416931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27880001068115234},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C79585631","wikidata":"https://www.wikidata.org/wiki/Q431498","display_name":"Confirmation bias","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i38.40477","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40477","pdf_url":null,"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/40477","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/40477","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.v40i38.40477","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40477","pdf_url":null,"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4,56],"increasingly":[5],"employed":[6],"in":[7,40,46,82],"applications":[8],"that":[9,140],"require":[10],"processing":[11,214],"information":[12,150],"from":[13],"heterogeneous":[14,35,212],"formats,":[15],"including":[16],"texts,":[17],"tables,":[18],"infoboxes,":[19],"and":[20,43,63,95,128,154,157,187,196,210],"knowledge":[21],"graphs.":[22],"However,":[23],"systematic":[24],"biases":[25,55],"toward":[26],"particular":[27],"formats":[28],"may":[29],"undermine":[30],"LLMs'":[31,125],"ability":[32],"to":[33,133,177],"integrate":[34],"data":[36,182,213],"impartially,":[37],"potentially":[38],"resulting":[39],"reasoning":[41],"errors":[42],"increased":[44],"risks":[45],"downstream":[47],"tasks.":[48],"Yet":[49],"it":[50],"remains":[51],"unclear":[52],"whether":[53],"such":[54,192],"systematic,":[57],"which":[58],"data-level":[59,111],"factors":[60,112],"drive":[61],"them,":[62],"what":[64],"internal":[65],"mechanisms":[66],"underlie":[67],"their":[68],"emergence.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73,171],"present":[74],"the":[75,93,165,205],"first":[76,90],"comprehensive":[77],"study":[78],"of":[79,97,103,207],"format":[80,121,141,179,185],"bias":[81,98,122,142],"LLMs":[83],"through":[84,184],"a":[85,100,130],"three-stage":[86],"empirical":[87],"analysis.":[88],"The":[89,105,116],"stage":[91,107,118],"explores":[92],"presence":[94],"direction":[96],"across":[99,145],"diverse":[101],"range":[102],"LLMs.":[104,166],"second":[106],"examines":[108],"how":[109,120],"key":[110],"influence":[113],"these":[114,169],"biases.":[115],"third":[117],"analyzes":[119],"emerges":[123],"within":[124,164],"attention":[126,162,194],"patterns":[127],"evaluates":[129],"lightweight":[131],"intervention":[132],"test":[134],"its":[135],"effectiveness.":[136],"Our":[137],"results":[138],"show":[139],"is":[143,158],"consistent":[144],"model":[146],"families,":[147],"driven":[148],"by":[149],"richness,":[151],"structure":[152],"quality,":[153],"representation":[155],"type,":[156],"closely":[159],"associated":[160],"with":[161],"imbalance":[163],"Based":[167],"on":[168],"investigations,":[170],"identify":[172],"three":[173],"future":[174],"research":[175],"directions":[176,202],"reduce":[178],"bias:":[180],"enhancing":[181],"pre-processing":[183],"repair":[186],"normalization,":[188],"introducing":[189],"inference-time":[190],"interventions":[191],"as":[193],"re-weighting,":[195],"developing":[197],"format-balanced":[198],"training":[199],"corpora.":[200],"These":[201],"will":[203],"support":[204],"design":[206],"more":[208],"robust":[209],"fair":[211],"systems.":[215]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}