{"id":"https://openalex.org/W4416034120","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1046","title":"Adaptive Preference Optimization with Uncertainty-aware Utility Anchor","display_name":"Adaptive Preference Optimization with Uncertainty-aware Utility Anchor","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034120","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1046"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1046","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1046","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1046.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.1046.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083636962","display_name":"Xiaobo Wang","orcid":"https://orcid.org/0000-0001-7892-5343"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaobo Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014045777","display_name":"Zixia Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zixia Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325928","display_name":"Jiaqi Li","orcid":"https://orcid.org/0000-0001-8198-5160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaqi Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453144","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0001-5378-6404"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056521090","display_name":"Zilong Zheng","orcid":"https://orcid.org/0000-0003-1219-5151"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zilong Zheng","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":"19204","last_page":"19225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11413","display_name":"Risk and Portfolio Optimization","score":0.149399995803833,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11413","display_name":"Risk and Portfolio Optimization","score":0.149399995803833,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.14740000665187836,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.13199999928474426,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.384799987077713},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.28690001368522644},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.26919999718666077},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.2547999918460846},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.2531999945640564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5052000284194946},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2930000126361847},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2615000009536743},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1046","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1046","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1046.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.1046","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1046","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1046.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/G3619655896","display_name":null,"funder_award_id":"62376031","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5540768979","display_name":null,"funder_award_id":"62337001","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034120.pdf","grobid_xml":"https://content.openalex.org/works/W4416034120.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Offline":[0],"preference":[1,71,92,144],"optimization":[2,13,72,145],"methods":[3,31],"are":[4],"efficient":[5],"for":[6,24,50,69,139],"large":[7],"language":[8],"models":[9],"(LLMs)":[10],"alignment.Direct":[11],"Preference":[12,75],"(DPO)like":[14],"learning,":[15],"one":[16],"of":[17],"the":[18,34,48,88,102,111,119,130,137],"most":[19],"popular":[20],"approaches,":[21],"stands":[22],"out":[23],"its":[25],"efficiency":[26],"in":[27,99,118],"reward":[28,40],"modeling.However,":[29],"these":[30,62],"typically":[32],"follow":[33],"convention":[35],"to":[36,86],"use":[37],"Bradley-Terry":[38],"(BT)":[39],"modeling":[41],"that":[42,124],"faces":[43],"several":[44],"critical":[45],"assumptions,":[46],"including":[47],"requirement":[49],"pairwise":[51],"training":[52,97,120],"data,":[53],"model":[54],"distribution":[55],"shifting,":[56],"human":[57],"rationality":[58],"assumption,":[59],"etc.To":[60],"address":[61],"limitations,":[63],"we":[64],"propose":[65],"a":[66],"general":[67],"framework":[68],"offline":[70],"methods,":[73],"Adaptive":[74],"Optimization":[76],"with":[77],"Utility":[78],"Anchor":[79],"(UAPO),":[80],"which":[81],"introduces":[82],"an":[83],"anchoring":[84],"function":[85],"estimate":[87],"uncertainties":[89],"brought":[90],"from":[91],"data":[93,103,108,134],"annotation.Our":[94],"method":[95],"enables":[96],"even":[98],"scenarios":[100],"where":[101],"is":[104],"unpaired,":[105],"significantly":[106],"enhancing":[107],"utilization":[109],"efficiency.Moreover,":[110],"anchor":[112],"design":[113],"makes":[114],"UAPO":[115,125],"more":[116,140],"robust":[117],"process.Experimental":[121],"results":[122],"demonstrate":[123],"achieves":[126],"competitive":[127],"outcomes":[128],"without":[129],"strict":[131],"dependency":[132],"on":[133],"pairing,":[135],"paving":[136],"way":[138],"flexible":[141],"and":[142],"effective":[143],"methods.":[146]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}