{"id":"https://openalex.org/W4412945000","doi":"https://doi.org/10.18653/v1/2025.acl-long.954","title":"IPO: Your Language Model is Secretly a Preference Classifier","display_name":"IPO: Your Language Model is Secretly a Preference Classifier","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945000","doi":"https://doi.org/10.18653/v1/2025.acl-long.954"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.954","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.954","pdf_url":"https://aclanthology.org/2025.acl-long.954.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.954.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102305762","display_name":"Shivank Garg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shivank Garg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034271698","display_name":"Ayush Singh","orcid":"https://orcid.org/0000-0002-4737-3424"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ayush Singh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100642841","display_name":"Shweta Singh","orcid":"https://orcid.org/0000-0002-1561-2494"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shweta Singh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Paras Chopra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paras Chopra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87853943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"19425","last_page":"19441"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13851","display_name":"Law, AI, and Intellectual Property","score":0.33469998836517334,"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"}},"topics":[{"id":"https://openalex.org/T13851","display_name":"Law, AI, and Intellectual Property","score":0.33469998836517334,"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/computer-science","display_name":"Computer science","score":0.6562222838401794},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5591581463813782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5365870594978333},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5168071985244751},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42261356115341187},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4099968671798706},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08921274542808533},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08257156610488892}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6562222838401794},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5591581463813782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5365870594978333},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5168071985244751},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42261356115341187},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4099968671798706},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08921274542808533},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08257156610488892}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.954","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.954","pdf_url":"https://aclanthology.org/2025.acl-long.954.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.954","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.954","pdf_url":"https://aclanthology.org/2025.acl-long.954.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945000.pdf","grobid_xml":"https://content.openalex.org/works/W4412945000.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"from":[2],"human":[3,19,72],"feedback":[4,73],"(RLHF)":[5],"has":[6],"emerged":[7],"as":[8,63,126],"the":[9,68,85,108,123],"primary":[10],"method":[11],"for":[12,117,130,152],"aligning":[13],"large":[14],"language":[15],"models":[16,44,76,94,139,151],"(LLMs)":[17],"with":[18],"preferences.While":[20],"it":[21,28],"enables":[22],"LLMs":[23,62,90,112],"to":[24,37,77,102,146],"achieve":[25,143],"human-level":[26],"alignment,":[27],"often":[29],"incurs":[30],"significant":[31],"computational":[32],"and":[33,99,121],"financial":[34],"costs":[35],"due":[36],"its":[38],"reliance":[39],"on":[40,70,84],"training":[41,100],"external":[42,71],"reward":[43,75,150],"or":[45,74],"human-labeled":[46],"preferences.In":[47],"this":[48],"work,":[49],"we":[50,106],"propose":[51],"Implicit":[52],"Preference":[53,132],"Optimization":[54,133],"(IPO),":[55],"an":[56],"alternative":[57],"approach":[58],"that":[59,138],"leverages":[60],"generative":[61],"preference":[64,86,128],"classifiers,":[65],"thereby":[66],"reducing":[67],"dependence":[69],"obtain":[78],"preferences.We":[79],"conduct":[80],"a":[81,118,127],"comprehensive":[82],"evaluation":[83],"classification":[87],"ability":[88],"of":[89,111],"using":[91],"RewardBench,":[92],"assessing":[93],"across":[95],"different":[96],"sizes,":[97],"architectures,":[98],"levels":[101],"validate":[103],"our":[104],"hypothesis.Furthermore,":[105],"investigate":[107],"self-improvement":[109],"capabilities":[110],"by":[113],"generating":[114],"multiple":[115],"responses":[116],"given":[119],"instruction":[120],"employing":[122],"model":[124],"itself":[125],"classifier":[129],"Direct":[131],"(DPO)-based":[134],"training.Our":[135],"findings":[136],"demonstrate":[137],"trained":[140],"through":[141],"IPO":[142],"performance":[144],"comparable":[145],"those":[147],"utilizing":[148],"state-of-the-art":[149],"obtaining":[153],"preferences.Our":[154],"code":[155],"is":[156],"available":[157],"at":[158],"https://github.com/shivank21/":[159],"Implicit_Preference_Optimization.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}