{"id":"https://openalex.org/W4416035951","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.183","title":"Not All Voices Are Rewarded Equally: Probing and Repairing Reward Models across Human Diversity","display_name":"Not All Voices Are Rewarded Equally: Probing and Repairing Reward Models across Human Diversity","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035951","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.183"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.183","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.183","pdf_url":"https://aclanthology.org/2025.findings-emnlp.183.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.183.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001895678","display_name":"Zihao Li","orcid":"https://orcid.org/0009-0009-7840-3364"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zihao Li","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073967955","display_name":"Fan Fang","orcid":"https://orcid.org/0000-0003-0382-1990"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feihao Fang","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084944008","display_name":"Xitong Zhang","orcid":"https://orcid.org/0000-0002-4379-8089"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xitong Zhang","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051330767","display_name":"Jiaru Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaru Zou","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101641279","display_name":"Zhining Liu","orcid":"https://orcid.org/0000-0002-2723-5999"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhining Liu","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101398340","display_name":"Wei Xiong","orcid":"https://orcid.org/0000-0001-8679-6086"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Xiong","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101794936","display_name":"Ziwei Wu","orcid":"https://orcid.org/0000-0003-3999-4367"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziwei Wu","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077678202","display_name":"Baoyu Jing","orcid":"https://orcid.org/0000-0003-1564-6499"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baoyu Jing","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073158087","display_name":"Jingrui He","orcid":"https://orcid.org/0000-0002-6429-6272"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingrui He","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39119922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3426","last_page":"3455"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10314","display_name":"Social and Intergroup Psychology","score":0.08560000360012054,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10314","display_name":"Social and Intergroup Psychology","score":0.08560000360012054,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11118","display_name":"Evolutionary Psychology and Human Behavior","score":0.06589999794960022,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.06210000067949295,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"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/diversity","display_name":"Diversity (politics)","score":0.48080000281333923},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.26840001344680786},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.26739999651908875},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.265500009059906},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.2621999979019165}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4973999857902527},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.38850000500679016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3328000009059906},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3301999866962433},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.183","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.183","pdf_url":"https://aclanthology.org/2025.findings-emnlp.183.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.183","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.183","pdf_url":"https://aclanthology.org/2025.findings-emnlp.183.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7374246537","display_name":"III: Small: RareXplain: A Computational Framework for Explainable Rare Category Analysis","funder_award_id":"2117902","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035951.pdf","grobid_xml":"https://content.openalex.org/works/W4416035951.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"advancement":[1],"of":[2,17],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"has":[7],"made":[8],"ensuring":[9],"their":[10],"trustworthiness":[11],"increasingly":[12],"critical,":[13],"especially":[14],"in":[15,158],"terms":[16],"fairness":[18],"across":[19,83,111],"diverse":[20],"human":[21],"groups.While":[22],"modern":[23],"LLMs":[24],"are":[25,43,62],"aligned":[26],"with":[27,143],"user":[28,132],"preferences":[29],"through":[30],"Reinforcement":[31],"Learning":[32],"from":[33,56],"Human":[34],"Feedback":[35],"(RLHF),":[36],"the":[37,100,124,136,151],"reward":[38,77,109,128,137,159],"models":[39,78,110,129],"used":[40],"for":[41],"alignment":[42],"trained":[44],"on":[45,146],"preference":[46,139],"data":[47],"that":[48,76],"may":[49],"both":[50,122],"reflect":[51],"societal":[52],"biases":[53],"and":[54,93,130,134],"suffer":[55],"demographic":[57,85],"skewness,":[58],"as":[59],"labeler":[60],"populations":[61],"often":[63],"uneven":[64],"due":[65],"to":[66,91,104,154],"systemic":[67],"accessibility":[68],"or":[69],"participation":[70],"gaps.In":[71],"this":[72],"work,":[73],"we":[74,98,149],"reveal":[75],"can":[79],"exhibit":[80],"significant":[81],"discrepancies":[82],"different":[84,144],"groups,":[86,133],"posing":[87],"a":[88],"fundamental":[89],"challenge":[90],"fair":[92],"robust":[94],"alignment.Using":[95],"real-world":[96],"datasets,":[97],"conduct":[99],"most":[101],"comprehensive":[102],"study":[103],"date,":[105],"auditing":[106],"various":[107],"state-of-the-art":[108],"nine":[112],"sensitive":[113],"attributes,":[114],"including":[115],"age,":[116],"gender,":[117],"ethnicity,":[118],"etc.Our":[119],"evaluation":[120],"spans":[121],"(1)":[123],"agreement":[125],"level":[126],"between":[127],"specific":[131],"(2)":[135],"model's":[138],"toward":[140],"responses":[141],"associated":[142],"groups.Based":[145],"these":[147],"findings,":[148],"propose":[150],"first":[152],"method":[153],"mitigate":[155],"group":[156],"disparities":[157],"modeling.Code":[160],"is":[161],"available":[162],"at":[163],"https://github.com/Violet24K/FaRM.":[164]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-08T00:00:00"}
