{"id":"https://openalex.org/W4412888334","doi":"https://doi.org/10.18653/v1/2025.findings-acl.574","title":"Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment","display_name":"Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888334","doi":"https://doi.org/10.18653/v1/2025.findings-acl.574"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.574","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.574","pdf_url":"https://aclanthology.org/2025.findings-acl.574.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 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-acl.574.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104285550","display_name":"Moxin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moxin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102775607","display_name":"Yuantao Zhang","orcid":"https://orcid.org/0000-0002-8671-6979"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuantao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368524","display_name":"Wenjie Wang","orcid":"https://orcid.org/0000-0002-5199-1428"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjie Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034482988","display_name":"Wentao Shi","orcid":"https://orcid.org/0000-0002-0847-9701"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wentao Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101057369","display_name":"Zhuo Liu","orcid":"https://orcid.org/0009-0003-4701-7408"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuo Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051925942","display_name":"Fuli Feng","orcid":"https://orcid.org/0000-0002-5828-9842"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fuli Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","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":"11010","last_page":"11031"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10315","display_name":"Decision-Making and Behavioral Economics","score":0.6334999799728394,"subfield":{"id":"https://openalex.org/subfields/1800","display_name":"General Decision Sciences"},"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/T10315","display_name":"Decision-Making and Behavioral Economics","score":0.6334999799728394,"subfield":{"id":"https://openalex.org/subfields/1800","display_name":"General Decision Sciences"},"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":0.6208000183105469,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5442000031471252,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.7384534478187561},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.7291741371154785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6177691221237183},{"id":"https://openalex.org/keywords/pareto-optimal","display_name":"Pareto optimal","score":0.5321174263954163},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.4225842356681824},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3703612685203552},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18526706099510193},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.14396515488624573},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.14132791757583618},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11184114217758179}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7384534478187561},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.7291741371154785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6177691221237183},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.5321174263954163},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.4225842356681824},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3703612685203552},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18526706099510193},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.14396515488624573},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.14132791757583618},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11184114217758179}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.574","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.574","pdf_url":"https://aclanthology.org/2025.findings-acl.574.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 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.574","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.574","pdf_url":"https://aclanthology.org/2025.findings-acl.574.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 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888334.pdf","grobid_xml":"https://content.openalex.org/works/W4412888334.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1963790170","https://openalex.org/W4318426920","https://openalex.org/W2073298047","https://openalex.org/W2033790662","https://openalex.org/W2090178682","https://openalex.org/W2586328217","https://openalex.org/W2049264236","https://openalex.org/W4241467429","https://openalex.org/W2337862504","https://openalex.org/W2067496256"],"abstract_inverted_index":{"Multi-Objective":[0],"Alignment":[1],"(MOA)":[2],"aims":[3],"to":[4,59,63,82,106],"align":[5],"LLMs'":[6],"responses":[7,62,87],"with":[8,13],"multiple":[9],"human":[10],"preference":[11,32,65,90],"objectives,":[12],"Direct":[14],"Preference":[15],"Optimization":[16],"(DPO)":[17],"emerging":[18],"as":[19],"a":[20,75],"prominent":[21],"approach.However,":[22],"we":[23,57,73],"find":[24],"that":[25,79],"DPO-based":[26],"MOA":[27],"approaches":[28],"suffer":[29],"from":[30],"widespread":[31],"conflicts":[33],"in":[34,44],"the":[35,49,52,97],"data,":[36],"where":[37],"different":[38,41],"objectives":[39],"favor":[40],"responses.This":[42],"results":[43],"conflicting":[45],"optimization":[46,50],"directions,":[47],"hindering":[48],"on":[51,93],"Pareto":[53,99],"Front.To":[54],"address":[55],"this,":[56],"propose":[58,74],"construct":[60],"Paretooptimal":[61],"resolve":[64],"conflicts.To":[66],"efficiently":[67],"obtain":[68],"and":[69,84],"utilize":[70],"such":[71],"responses,":[72],"self-improving":[76],"DPO":[77],"framework":[78,104],"enables":[80],"LLMs":[81],"self-generate":[83],"select":[85],"Pareto-optimal":[86],"for":[88],"selfsupervised":[89],"alignment.Extensive":[91],"experiments":[92],"two":[94],"datasets":[95],"demonstrate":[96],"superior":[98],"Front":[100],"achieved":[101],"by":[102],"our":[103],"compared":[105],"various":[107],"baselines":[108],"1":[109],".":[110]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}