{"id":"https://openalex.org/W4416035036","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.300","title":"SPO: Self Preference Optimization with Self Regularization","display_name":"SPO: Self Preference Optimization with Self Regularization","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035036","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.300"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.300","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.300","pdf_url":"https://aclanthology.org/2025.findings-emnlp.300.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.300.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055842287","display_name":"Yuhao Sun","orcid":"https://orcid.org/0000-0001-6987-3721"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhao Sun","raw_affiliation_strings":["Xiaomi Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376929","display_name":"Yifan Zhang","orcid":"https://orcid.org/0000-0002-0629-0200"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Zhang","raw_affiliation_strings":["Xiaomi Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013004114","display_name":"Quandong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quandong Wang","raw_affiliation_strings":["Xiaomi Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064887293","display_name":"Qinzhuo Wu","orcid":"https://orcid.org/0000-0002-9511-0258"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinzhuo Wu","raw_affiliation_strings":["Xiaomi Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060714163","display_name":"Liu We","orcid":"https://orcid.org/0000-0001-6111-4149"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Xiaomi Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050757052","display_name":"Jian Luan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Luan","raw_affiliation_strings":["Xiaomi Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc","institution_ids":[]}]}],"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":"5601","last_page":"5614"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.43140000104904175,"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"}},"topics":[{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.43140000104904175,"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"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.08619999885559082,"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":0.040699999779462814,"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/regularization","display_name":"Regularization (linguistics)","score":0.39309999346733093},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.3637000024318695},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.3391999900341034},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.2782999873161316}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4754999876022339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4025999903678894},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34940001368522644},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3224000036716461},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.300","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.300","pdf_url":"https://aclanthology.org/2025.findings-emnlp.300.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.300","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.300","pdf_url":"https://aclanthology.org/2025.findings-emnlp.300.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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035036.pdf","grobid_xml":"https://content.openalex.org/works/W4416035036.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Direct":[0],"Preference":[1,30,35,72],"Optimization":[2,73],"(DPO)":[3],"is":[4,117],"a":[5,92,152],"widely":[6],"used":[7],"offline":[8],"preference":[9,40],"optimization":[10,41],"algorithm":[11],"that":[12,49,113,126,149],"enhances":[13],"the":[14,76,81,96,101,114,122,128,133],"simplicity":[15],"and":[16,32,106,145],"training":[17,46,55],"stability":[18],"of":[19,121],"reinforcement":[20],"learning":[21],"through":[22],"reward":[23],"function":[24,78,87],"reparameterization":[25],"from":[26,98],"PPO.Recently,":[27],"SimPO":[28,156],"(Simple":[29],"Optimization)":[31,36],"CPO":[33],"(Contrastive":[34],"have":[37],"proposed":[38],"reference-free":[39,51],"methods":[42,52],"to":[43,60,63,79],"simplify":[44],"DPO's":[45],"process.We":[47],"observe":[48],"these":[50,67],"exhibit":[53],"higher":[54],"efficiency":[56],"but":[57],"are":[58],"prone":[59],"overoptimization,":[61],"leading":[62],"performance":[64,167],"degradation.To":[65],"address":[66],"issues,":[68],"we":[69],"propose":[70],"Self":[71],"(SPO).SPO":[74],"employs":[75],"SiLU":[77,86],"replace":[80],"conventional":[82],"logsigmoid":[83],"loss":[84,116],"function.The":[85],"attains":[88],"its":[89],"minimum":[90],"at":[91],"finite":[93],"value,":[94],"preventing":[95],"model":[97],"excessively":[99],"amplifying":[100],"chosenrejected":[102],"sample":[103],"probability":[104],"ratio":[105],"thereby":[107],"mitigating":[108],"overoptimization":[109],"problem.We":[110],"theoretically":[111],"demonstrate":[112],"SPO":[115,129,150],"an":[118],"upper":[119],"bound":[120],"DPO":[123,134],"loss,":[124],"implying":[125],"optimizing":[127],"objective":[130],"implicitly":[131],"optimizes":[132],"objective.We":[135],"evaluate":[136],"SPO's":[137],"effectiveness":[138],"across":[139],"multiple":[140],"benchmarks":[141],"including":[142],"AlpacaEval":[143,162],"2":[144],"MT-Bench.Experimental":[146],"results":[147],"show":[148],"achieves":[151],"7%":[153],"improvement":[154],"over":[155],"in":[157],"length-controlled":[158],"win":[159],"rate":[160],"on":[161,168],"2,":[163],"while":[164],"demonstrating":[165],"superior":[166],"MT-Bench.":[169]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}