{"id":"https://openalex.org/W4412886892","doi":"https://doi.org/10.18653/v1/2025.acl-long.6","title":"Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process","display_name":"Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886892","doi":"https://doi.org/10.18653/v1/2025.acl-long.6"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.6","pdf_url":"https://aclanthology.org/2025.acl-long.6.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.6.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094087237","display_name":"Ermo Hua","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ermo Hua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113291945","display_name":"Biqing Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biqing Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101999480","display_name":"Kaiyan Zhang","orcid":"https://orcid.org/0000-0003-4650-5242"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaiyan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061070261","display_name":"Kai Tian","orcid":"https://orcid.org/0000-0003-0224-4466"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108934300","display_name":"Xingtai Lv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingtai Lv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101614766","display_name":"Ning Ding","orcid":"https://orcid.org/0000-0002-1321-9314"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004875850","display_name":"Bowen Zhou","orcid":"https://orcid.org/0000-0003-4421-9787"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bowen Zhou","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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.429500013589859,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.429500013589859,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6979361176490784},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6443982124328613},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1398780345916748}],"concepts":[{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6979361176490784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6443982124328613},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1398780345916748}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.6","pdf_url":"https://aclanthology.org/2025.acl-long.6.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.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.6","pdf_url":"https://aclanthology.org/2025.acl-long.6.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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4000000059604645}],"awards":[],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886892.pdf","grobid_xml":"https://content.openalex.org/works/W4412886892.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":{"Supervised":[0],"Fine-Tuning":[1,136],"(SFT)":[2],"and":[3,24,47,58,65,92,127,141,155,173,193,206],"Preference":[4],"Optimization":[5,67],"(PO)":[6],"are":[7,29],"key":[8],"processes":[9],"for":[10,219],"aligning":[11],"Language":[12],"Models":[13],"(LMs)":[14],"with":[15,60,89],"human":[16],"preferences":[17],"post":[18],"pre-training.While":[19],"SFT":[20,57,81,103,140,192],"excels":[21],"in":[22,26],"efficiency":[23],"PO":[25,59,88,142,196],"effectiveness,":[27],"they":[28],"often":[30],"combined":[31],"sequentially":[32],"without":[33],"integrating":[34],"their":[35,44],"optimization":[36,156],"objectives.This":[37],"approach":[38],"ignores":[39],"the":[40,49,73,95,124,174,215],"opportunities":[41],"to":[42,138,191],"bridge":[43],"paradigm":[45],"gap":[46],"take":[48],"strengths":[50],"from":[51,114,120],"both.In":[52],"this":[53,131],"paper,":[54],"we":[55,133],"interpret":[56],"two":[61],"subprocesses":[62],"-Preference":[63],"Estimation":[64],"Transition":[66],"-defined":[68],"at":[69],"token":[70],"level":[71],"within":[72],"Markov":[74],"Decision":[75],"Process":[76],"(MDP).This":[77],"modeling":[78],"shows":[79],"that":[80,184],"is":[82],"only":[83,104],"a":[84,144,147,170],"special":[85],"case":[86],"of":[87,162,177,217],"inferior":[90],"estimation":[91,126,154],"optimization.PO":[93],"estimates":[94],"model's":[96,106,121],"preference":[97,125],"by":[98,157],"its":[99,163],"entire":[100,164],"generation,":[101,204],"while":[102],"scores":[105],"subsequent":[107],"predicted":[108],"tokens":[109,113],"based":[110],"on":[111,130,169],"prior":[112],"ground":[115],"truth":[116],"answer.These":[117],"priors":[118],"deviates":[119],"distribution,":[122],"hindering":[123],"transition":[128],"optimization.Building":[129],"view,":[132],"introduce":[134],"Intuitive":[135],"(IFT)":[137],"integrate":[139],"into":[143],"single":[145,171],"process.Through":[146],"temporal":[148],"residual":[149],"connection,":[150],"IFT":[151,185,218],"brings":[152],"better":[153],"capturing":[158],"LMs'":[159],"intuitive":[160],"sense":[161],"answers.But":[165],"it":[166],"solely":[167],"relies":[168],"policy":[172],"same":[175],"volume":[176],"non-preference-labeled":[178],"data":[179],"as":[180],"SFT.Our":[181],"experiments":[182],"show":[183],"performs":[186],"comparably":[187],"or":[188],"even":[189],"superiorly":[190],"some":[194],"typical":[195],"methods":[197],"across":[198],"several":[199],"tasks,":[200],"particularly":[201],"those":[202],"requires":[203],"reasoning,":[205],"fact-following":[207],"abilities.An":[208],"explainable":[209],"Frozen":[210],"Lake":[211],"game":[212],"further":[213],"validates":[214],"effectiveness":[216],"getting":[220],"competitive":[221],"policy.":[222]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}