{"id":"https://openalex.org/W7166800331","doi":"https://doi.org/10.18653/v1/2026.findings-acl.269","title":"Understanding Conflicts in Multi-Objective Alignment through Reward Consistency","display_name":"Understanding Conflicts in Multi-Objective Alignment through Reward Consistency","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166800331","doi":"https://doi.org/10.18653/v1/2026.findings-acl.269"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.269","doi":"https://doi.org/10.18653/v1/2026.findings-acl.269","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.269","pdf_url":"https://aclanthology.org/2026.findings-acl.269.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-acl.269.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036719917","display_name":"Zhihao Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Xu","raw_affiliation_strings":["Beijing Key Laboratory of Research on Large Models and Intelligent Governance","Gaoling School of Artificial Intelligence , Renmin University of China Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Research on Large Models and Intelligent Governance","institution_ids":[]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China Beijing , China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114193246","display_name":"Yongqi Tong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqi Tong","raw_affiliation_strings":["Ant International ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant International ,","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139838455","display_name":"Xin Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["Ant International ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant International ,","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101706577","display_name":"Jun Zhou","orcid":"https://orcid.org/0000-0003-0462-1894","observed_orcids":["https://orcid.org/0000-0003-0462-1894"]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Zhou","raw_affiliation_strings":["Ant Group ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group ,","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139791005","display_name":"Xiting Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiting Wang","raw_affiliation_strings":["Beijing Key Laboratory of Research on Large Models and Intelligent Governance","Gaoling School of Artificial Intelligence , Renmin University of China Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Research on Large Models and Intelligent Governance","institution_ids":[]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China Beijing , China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.41108711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5450","last_page":"5472"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.2433999925851822,"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"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.2433999925851822,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0843999981880188,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.07360000163316727,"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/reward-models","display_name":"reward models","score":0.8489999771118164},{"id":"https://openalex.org/keywords/simultaneous-optimization","display_name":"simultaneous optimization","score":0.7860000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5123999714851379},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4068000018596649},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2583000063896179},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.23919999599456787},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.23770000040531158},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.22589999437332153},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2240999937057495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2240999937057495}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.269","doi":"https://doi.org/10.18653/v1/2026.findings-acl.269","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.269","pdf_url":"https://aclanthology.org/2026.findings-acl.269.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.269","doi":"https://doi.org/10.18653/v1/2026.findings-acl.269","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.269","pdf_url":"https://aclanthology.org/2026.findings-acl.269.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.6197260618209839,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G3248486410","display_name":null,"funder_award_id":"U2436209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4128466783","display_name":null,"funder_award_id":"92470205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6750762792","display_name":null,"funder_award_id":"62476279","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/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"},{"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/W7166800331.pdf","grobid_xml":"https://content.openalex.org/works/W7166800331.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416052740","https://openalex.org/W7127437642","https://openalex.org/W7161044514","https://openalex.org/W7083819128","https://openalex.org/W4413069756","https://openalex.org/W4401065967","https://openalex.org/W7208801890","https://openalex.org/W7164586971","https://openalex.org/W6979296412","https://openalex.org/W7214207561"],"abstract_inverted_index":{"Multi-objective":[0],"preference":[1],"alignment":[2,5,52,140],"often":[3],"faces":[4],"conflicts,":[6],"where":[7],"optimizing":[8],"for":[9,89],"one":[10],"objective":[11],"degrades":[12],"performance":[13,113],"on":[14,19,31,78],"others.While":[15],"prior":[16],"work":[17],"focuses":[18],"algorithmic":[20],"solutions,":[21],"the":[22,40,51,131],"intrinsic":[23],"conflict":[24],"within":[25],"data":[26,92],"and":[27,64,111,124,142,147],"its":[28],"theoretical":[29],"impact":[30],"training":[32],"remain":[33],"underexplored.To":[34],"bridge":[35],"this":[36],"gap,":[37],"we":[38,80],"introduce":[39],"principle":[41],"of":[42,119],"REWARD":[43],"CONSISTENCY":[44,83],"(RC),":[45],"a":[46,59,99],"theory-grounded":[47],"criterion":[48],"that":[49,58,93,107],"approximates":[50],"conflicts":[53,62],"via":[54],"reward":[55],"models.We":[56],"prove":[57],"sample":[60],"mitigates":[61],"if":[63,66],"only":[65],"it":[67],"satisfies":[68],"RC,":[69,96],"thereby":[70],"ensuring":[71],"improvement":[72,118],"across":[73],"all":[74],"objectives":[75],"during":[76,126],"optimization.Building":[77],"this,":[79],"propose":[81],"RE-WARD":[82],"SAMPLING":[84],"(RCS),":[85],"an":[86,116],"automated":[87],"framework":[88],"constructing":[90],"pairwise":[91],"adheres":[94],"to":[95,102,130,138],"supplemented":[97],"by":[98],"relaxation":[100],"strategy":[101],"enhance":[103],"flexibility.Extensive":[104],"experiments":[105],"show":[106],"RCS":[108],"brings":[109],"significant":[110],"consistent":[112],"gains,":[114],"achieving":[115],"average":[117],"23.07%":[120],"in":[121,144],"both":[122,145],"harmlessness":[123],"helpfulness":[125],"simultaneous":[127,148],"optimization":[128,149],"compared":[129],"vanilla":[132],"dataset.Our":[133],"data-centric":[134],"approach":[135],"is":[136],"complementary":[137],"existing":[139],"algorithms":[141],"effective":[143],"sequential":[146],"scenarios.":[150]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-02T00:00:00"}