{"id":"https://openalex.org/W4412888500","doi":"https://doi.org/10.18653/v1/2025.findings-acl.462","title":"AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models","display_name":"AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888500","doi":"https://doi.org/10.18653/v1/2025.findings-acl.462"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.462","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.462","pdf_url":"https://aclanthology.org/2025.findings-acl.462.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.462.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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":"middle","author":{"id":"https://openalex.org/A5076546255","display_name":"Jingqing Ruan","orcid":"https://orcid.org/0000-0002-4857-9053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingqing Ruan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348624","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-6739-2008"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Haodong Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haodong Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051153747","display_name":"D. Y. Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Desheng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087601044","display_name":"Jiansong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiansong Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181435","display_name":"Wan Guanglu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan Guanglu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114353815","display_name":"Xunliang Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xunliang Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040762883","display_name":"Zhi Zheng","orcid":"https://orcid.org/0000-0001-7758-8904"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhi Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100540419","display_name":"Xu Tong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong Xu","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8832","last_page":"8866"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.7473999857902527,"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"}},"topics":[{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.7473999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.7265904545783997},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6987433433532715},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17403429746627808},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11769336462020874}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7265904545783997},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6987433433532715},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17403429746627808},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11769336462020874}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.462","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.462","pdf_url":"https://aclanthology.org/2025.findings-acl.462.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.462","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.462","pdf_url":"https://aclanthology.org/2025.findings-acl.462.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":[{"id":"https://openalex.org/G3604000827","display_name":null,"funder_award_id":"62222213","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7295420491","display_name":null,"funder_award_id":"62072423","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/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888500.pdf","grobid_xml":"https://content.openalex.org/works/W4412888500.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Existing":[0],"multi-objective":[1,53],"preference":[2,19,49,97,140],"alignment":[3],"methods":[4],"for":[5],"large":[6],"language":[7],"models":[8,27,74,85,116],"(LLMs)":[9],"face":[10],"limitations:":[11],"(1)":[12],"the":[13,52,58,86,109,118],"inability":[14],"to":[15,56,137],"effectively":[16],"balance":[17,47],"various":[18],"dimensions,":[20],"and":[21,108,114,131,146],"(2)":[22],"reliance":[23],"on":[24,111],"auxiliary":[25],"reward/reference":[26],"introduces":[28],"computational":[29],"complexity.To":[30],"address":[31],"these":[32],"challenges,":[33],"we":[34],"propose":[35],"Adaptive":[36],"Multi-objective":[37],"Preference":[38],"Optimization":[39],"(AMoPO),":[40],"a":[41,90],"novel":[42],"framework":[43],"that":[44,84,101],"achieves":[45],"dynamic":[46,94],"across":[48],"dimensions.By":[50],"introducing":[51],"optimization":[54],"paradigm":[55],"use":[57],"dimension-aware":[59,139],"generation":[60,87],"metrics":[61],"as":[62,89],"implicit":[63],"rewards,":[64],"AMoPO":[65,102],"aligns":[66],"LLMs":[67],"with":[68],"diverse":[69],"preferences":[70],"without":[71],"additional":[72,123],"reward":[73],"or":[75],"reference":[76],"models.We":[77],"introduce":[78],"an":[79],"adaptive":[80],"weight":[81],"assignment":[82],"mechanism":[83],"space":[88],"Gaussian":[91],"distribution,":[92],"allowing":[93],"prioritization":[95],"of":[96,121,125],"dimensions.Empirical":[98],"results":[99],"demonstrate":[100],"outperforms":[103],"state-of-the-art":[104],"baselines":[105],"by":[106],"28.5%,":[107],"experiments":[110],"7B,":[112],"14B,":[113],"32B":[115],"reveal":[117],"scaling":[119],"ability":[120],"AMoPO.Moreover,":[122],"analysis":[124],"multiple":[126],"dimensions":[127],"verifies":[128],"its":[129,143],"adaptability":[130],"effectiveness.These":[132],"findings":[133],"validate":[134],"AMoPO's":[135],"capability":[136],"achieve":[138],"alignment,":[141],"highlighting":[142],"superiority.Our":[144],"codes":[145],"datasets":[147],"are":[148],"available":[149],"at":[150],"https://github.com/Javkonline/AMoPO.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}