{"id":"https://openalex.org/W4416383312","doi":"https://doi.org/10.18653/v1/2026.findings-acl.71","title":"Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling","display_name":"Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416383312","doi":"https://doi.org/10.18653/v1/2026.findings-acl.71"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.71","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.71","pdf_url":"https://aclanthology.org/2026.findings-acl.71.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: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.71.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115594080","display_name":"Shuliang Liu","orcid":"https://orcid.org/0000-0002-9633-8385"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuliang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100623388","display_name":"Zhipeng Xu","orcid":"https://orcid.org/0009-0003-0389-5620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhipeng Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070196864","display_name":"Zhenghao Liu","orcid":"https://orcid.org/0000-0001-8067-1477"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenghao Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034266748","display_name":"Yukun Yan","orcid":"https://orcid.org/0000-0003-2421-7098"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yukun Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073894049","display_name":"Minghe Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minghe Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066844892","display_name":"Yu Gu","orcid":"https://orcid.org/0000-0003-2353-063X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Gu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001857897","display_name":"Chong Chen","orcid":"https://orcid.org/0000-0001-7481-9172"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Huiyuan Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huiyuan Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100782393","display_name":"Ge Yu","orcid":"https://orcid.org/0000-0002-9359-2812"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge Yu","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02510905,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1448","last_page":"1464"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.15230000019073486,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.15230000019073486,"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/T10028","display_name":"Topic Modeling","score":0.13609999418258667,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.1054999977350235,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/polling","display_name":"Polling","score":0.8812999725341797},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.7366999983787537},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5037000179290771},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45419999957084656},{"id":"https://openalex.org/keywords/polling-system","display_name":"Polling system","score":0.365200012922287},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3061999976634979}],"concepts":[{"id":"https://openalex.org/C204854418","wikidata":"https://www.wikidata.org/wiki/Q1362921","display_name":"Polling","level":2,"score":0.8812999725341797},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7366999983787537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.644599974155426},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5037000179290771},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44190001487731934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37880000472068787},{"id":"https://openalex.org/C87190583","wikidata":"https://www.wikidata.org/wiki/Q17097337","display_name":"Polling system","level":3,"score":0.365200012922287},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3077999949455261},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C79585631","wikidata":"https://www.wikidata.org/wiki/Q431498","display_name":"Confirmation bias","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C3020452639","wikidata":"https://www.wikidata.org/wiki/Q454812","display_name":"Clinical judgment","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.271699994802475},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C108215451","wikidata":"https://www.wikidata.org/wiki/Q7263963","display_name":"Simulation modeling","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.71","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.71","pdf_url":"https://aclanthology.org/2026.findings-acl.71.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: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.08145","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.08145","pdf_url":"https://arxiv.org/pdf/2510.08145","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.08145","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.08145","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.71","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.71","pdf_url":"https://aclanthology.org/2026.findings-acl.71.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8502117127","display_name":null,"funder_award_id":"62576082","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416383312.pdf","grobid_xml":"https://content.openalex.org/works/W4416383312.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"as":[4,10,136],"automatic":[5],"evaluators,":[6],"commonly":[7],"referred":[8],"to":[9,46,98],"\"LLMas-a-Judge\",":[11],"have":[12],"also":[13],"attracted":[14],"growing":[15],"attention.This":[16],"approach":[17],"plays":[18],"a":[19,88],"vital":[20],"role":[21],"in":[22],"aligning":[23],"LLMs":[24],"with":[25],"human":[26],"judgments,":[27],"providing":[28],"accurate":[29],"and":[30,91],"reliable":[31],"assessments.However,":[32],"LLM-based":[33,84,149],"judgment":[34,38,75,79,85,114,145,150],"models":[35,86,110,134],"often":[36],"exhibit":[37],"preference":[39,76,146],"bias":[40,77,147],"during":[41,128],"the":[42,53,60,73,93,129],"evaluation":[43],"phase,":[44],"tending":[45],"favor":[47],"responses":[48],"generated":[49],"by":[50],"themselves,":[51],"undermining":[52],"reliability":[54],"of":[55,78,148],"their":[56],"judgments.This":[57],"paper":[58],"introduces":[59],"Group-Based":[61],"Polling":[62],"Optimization":[63],"(Genii),":[64],"an":[65],"unsupervised":[66],"multi-agent":[67,89],"collaborative":[68],"optimization":[69],"framework":[70],"that":[71,106,141],"mitigates":[72,144],"inherent":[74],"models.Specifically,":[80],"Genii":[81,107,142],"integrates":[82],"various":[83],"into":[87],"system":[90],"simulates":[92],"interactive":[94],"client-server":[95],"polling":[96],"mechanism":[97],"optimize":[99],"each":[100],"client":[101,126],"agent":[102],"unsupervisedly.Our":[103],"experiments":[104],"demonstrate":[105],"outperforms":[108],"supervised":[109],"trained":[111],"on":[112],"annotated":[113],"data,":[115],"while":[116],"requiring":[117],"no":[118],"human-labeled":[119],"annotations.Genii":[120],"consistently":[121],"improves":[122],"performance":[123],"across":[124],"different":[125],"agents":[127],"polling,":[130],"even":[131],"when":[132],"weaker":[133],"act":[135],"server":[137],"agents.Further":[138],"analysis":[139],"reveals":[140],"effectively":[143],"models,":[151],"demonstrating":[152],"its":[153],"effectiveness.All":[154],"codes":[155],"are":[156],"available":[157],"at":[158],"https://github.com/NEUIR/Genii.":[159]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-11T00:00:00"}