{"id":"https://openalex.org/W4417302185","doi":"https://doi.org/10.18653/v1/2026.acl-long.133","title":"Bias Fitting to Mitigate Length Bias of Reward Model in RLHF","display_name":"Bias Fitting to Mitigate Length Bias of Reward Model in RLHF","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417302185","doi":"https://doi.org/10.18653/v1/2026.acl-long.133"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.133","pdf_url":"https://aclanthology.org/2026.acl-long.133.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","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.acl-long.133.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kangwen Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kangwen Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101199142","display_name":"Jianfeng Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianfeng Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006165246","display_name":"J. Zhu","orcid":"https://orcid.org/0000-0003-2155-2659"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinhua Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ruopei Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruopei Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120793774","display_name":"Dongyun Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongyun Xue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361101","display_name":"Li Li","orcid":"https://orcid.org/0000-0002-1264-7819"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Houqiang Li","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":0.03665557,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2912","last_page":"2927"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.19850000739097595,"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":0.19850000739097595,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.08799999952316284,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.07959999889135361,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/relation","display_name":"Relation (database)","score":0.5307000279426575},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4163999855518341},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.41110000014305115},{"id":"https://openalex.org/keywords/omitted-variable-bias","display_name":"Omitted-variable bias","score":0.40209999680519104},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.3555000126361847},{"id":"https://openalex.org/keywords/learning-curve","display_name":"Learning curve","score":0.35089999437332153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6164000034332275},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5307000279426575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4722999930381775},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C6571938","wikidata":"https://www.wikidata.org/wiki/Q3274486","display_name":"Omitted-variable bias","level":2,"score":0.40209999680519104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.388700008392334},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.36809998750686646},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2939000129699707},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.2615000009536743}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.133","pdf_url":"https://aclanthology.org/2026.acl-long.133.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.12843","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.12843","pdf_url":"https://arxiv.org/pdf/2505.12843","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.12843","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.12843","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.133","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.133","pdf_url":"https://aclanthology.org/2026.acl-long.133.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1280917168","display_name":null,"funder_award_id":"623B2097","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"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320325599","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09"},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417302185.pdf","grobid_xml":"https://content.openalex.org/works/W4417302185.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Kangwen":[0],"Zhao,":[1],"Jianfeng":[2],"Cai,":[3],"Jinhua":[4],"Zhu,":[5],"Ruopei":[6],"Sun,":[7],"Dongyun":[8],"Xue,":[9],"Wengang":[10],"Zhou,":[11],"Li":[12],"Li,":[13],"Houqiang":[14],"Li.":[15],"Proceedings":[16],"of":[17,22],"the":[18,23],"64th":[19],"Annual":[20],"Meeting":[21],"Association":[24],"for":[25],"Computational":[26],"Linguistics":[27],"(Volume":[28],"1:":[29],"Long":[30],"Papers).":[31],"2026.":[32]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}