{"id":"https://openalex.org/W7166881405","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1879","title":"Beyond Compromise: Pareto-Lenient Consensus for Efficient Multi-Preference LLM Alignment","display_name":"Beyond Compromise: Pareto-Lenient Consensus for Efficient Multi-Preference LLM Alignment","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166881405","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1879"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1879","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1879","pdf_url":"https://aclanthology.org/2026.findings-acl.1879.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 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1879.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133156175","display_name":"Renxuan Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renxuan Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133155139","display_name":"Rongpeng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongpeng Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133199007","display_name":"Zhifeng Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhifeng Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139815695","display_name":"Honggang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Honggang 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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.92790302,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"37684","last_page":"37705"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10991","display_name":"Game Theory and Voting Systems","score":0.3492000102996826,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10991","display_name":"Game Theory and Voting Systems","score":0.3492000102996826,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.13930000364780426,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.13840000331401825,"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/context","display_name":"Context (archaeology)","score":0.27570000290870667},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.25429999828338623},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.25360000133514404},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2529999911785126},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.24770000576972961}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5443999767303467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.311599999666214},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.24770000576972961},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.23649999499320984},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.23240000009536743},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.23119999468326569}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1879","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1879","pdf_url":"https://aclanthology.org/2026.findings-acl.1879.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 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1879","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1879","pdf_url":"https://aclanthology.org/2026.findings-acl.1879.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 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7215740136","display_name":null,"funder_award_id":"2024YFE0200600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166881405.pdf","grobid_xml":"https://content.openalex.org/works/W7166881405.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Transcending":[0],"the":[1,60,114,124,161],"single-preference":[2],"paradigm,":[3],"aligning":[4],"LLMs":[5],"with":[6],"diverse":[7],"human":[8],"values":[9],"is":[10,106],"pivotal":[11],"for":[12,170],"robust":[13],"deployment.Contemporary":[14],"Multi-Objective":[15],"Preference":[16],"Alignment":[17],"(MPA)":[18],"approaches":[19],"predominantly":[20],"rely":[21],"on":[22],"static":[23],"linear":[24],"scalarization":[25],"or":[26,39],"rigid":[27,91],"gradient":[28,97],"projection":[29],"to":[30,47,67,117,138],"navigate":[31],"these":[32,42,53],"trade-offs.However,":[33],"by":[34],"enforcing":[35],"strict":[36],"conflict":[37],"avoidance":[38],"simultaneous":[40],"descent,":[41],"paradigms":[43],"often":[44],"prematurely":[45],"converge":[46,137],"local":[48,70,102,119],"stationary":[49],"points.While":[50],"mathematically":[51],"stable,":[52],"points":[54],"represent":[55],"a":[56,80,87,107,139,167],"conservative":[57],"compromise":[58],"where":[59],"model":[61],"sacrifices":[62],"potential":[63,162],"global":[64,155],"Pareto":[65,140,156],"improvements":[66],"avoid":[68],"transient":[69],"trade-offs.To":[71],"break":[72],"this":[73],"deadlock,":[74],"we":[75],"propose":[76],"Pareto-Lenient":[77],"Consensus":[78],"(PLC),":[79],"game-theoretic":[81],"framework":[82],"that":[83,146],"reimagines":[84],"alignment":[85,153,165],"as":[86,166],"dynamic":[88],"negotiation":[89],"process.Unlike":[90],"approaches,":[92],"PLC":[93,130,147],"introduces":[94],"consensus-driven":[95],"lenient":[96],"rectification,":[98],"which":[99],"dynamically":[100],"tolerates":[101],"degradation":[103],"provided":[104],"there":[105],"sufficient":[108],"dominant":[109],"coalition":[110],"surplus,":[111],"thereby":[112],"empowering":[113],"optimization":[115],"trajectory":[116],"escape":[118,134],"suboptimal":[120],"equilibrium":[121],"and":[122,135,154],"explore":[123],"distal":[125],"Pareto-optimal":[126],"frontier.Theoretical":[127],"analysis":[128],"validates":[129],"can":[131],"facilitate":[132],"stalemate":[133],"asymptotically":[136],"consensus":[141],"equilibrium.Moreover,":[142],"extensive":[143],"experiments":[144],"show":[145],"surpasses":[148],"baselines":[149],"in":[150],"both":[151],"fixed-preference":[152],"frontier":[157],"quality.This":[158],"work":[159],"highlights":[160],"of":[163],"negotiation-driven":[164],"promising":[168],"avenue":[169],"MPA.Our":[171],"codes":[172],"are":[173],"available":[174],"at":[175],"https://github.com/lakjx/":[176],"consensus-equilibra.":[177]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}