{"id":"https://openalex.org/W4416033888","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1237","title":"DORM: Preference Data Weights Optimization for Reward Modeling in LLM Alignment","display_name":"DORM: Preference Data Weights Optimization for Reward Modeling in LLM Alignment","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033888","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1237"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1237","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1237","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1237.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1237.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089455757","display_name":"Rongzhi Zhang","orcid":"https://orcid.org/0000-0002-7136-7913"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongzhi Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017147857","display_name":"Chenwei Zhang","orcid":"https://orcid.org/0000-0002-0488-4603"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenwei Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072160668","display_name":"Xinyang Zhang","orcid":"https://orcid.org/0000-0002-3497-7448"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089950789","display_name":"Liang Qiu","orcid":"https://orcid.org/0000-0001-5671-2558"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Qiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030361161","display_name":"Haoming Jiang","orcid":"https://orcid.org/0000-0003-0789-525X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoming Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063200221","display_name":"Yuchen Zhuang","orcid":"https://orcid.org/0000-0003-4641-894X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuchen Zhuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059657111","display_name":"Qingru Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingru Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061527181","display_name":"Hyokun Yun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyokun Yun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113740084","display_name":"Xian Li","orcid":"https://orcid.org/0009-0005-7563-503X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xian Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bing Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bing Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109592386","display_name":"Tuo Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuo Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000136911","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0001-5452-801X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Zhang","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":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22721","last_page":"22739"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2766000032424927,"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":0.2766000032424927,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.07000000029802322,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.06080000102519989,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/preference","display_name":"Preference","score":0.48159998655319214},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3084999918937683},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.2957000136375427},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.28540000319480896},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.27149999141693115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5008999705314636},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.48159998655319214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4799000024795532},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32089999318122864},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2851000130176544},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2838999927043915},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1237","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1237","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1237.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.1237","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1237","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1237.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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416033888.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Rongzhi":[0],"Zhang,":[1,3,5,13],"Chenwei":[2],"Xinyang":[4],"Liang":[6],"Qiu,":[7],"Haoming":[8],"Jiang,":[9],"Yuchen":[10],"Zhuang,":[11],"Qingru":[12],"Hyokun":[14],"Yun,":[15],"Xian":[16],"Li,":[17],"Bing":[18],"Yin,":[19],"Tuo":[20],"Zhao,":[21],"Chao":[22],"Zhang.":[23],"Findings":[24],"of":[25],"the":[26],"Association":[27],"for":[28],"Computational":[29],"Linguistics:":[30],"EMNLP":[31],"2025.":[32,33]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}