{"id":"https://openalex.org/W4412888469","doi":"https://doi.org/10.18653/v1/2025.findings-acl.473","title":"Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models","display_name":"Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888469","doi":"https://doi.org/10.18653/v1/2025.findings-acl.473"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.473","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.473","pdf_url":"https://aclanthology.org/2025.findings-acl.473.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.473.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100685027","display_name":"Hao Xiang","orcid":"https://orcid.org/0000-0003-0902-0115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101188063","display_name":"Bowen Yu","orcid":"https://orcid.org/0009-0008-9642-7880"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bowen Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100314185","display_name":"Hongyu Lin","orcid":"https://orcid.org/0009-0008-0312-3256"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyu Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018680558","display_name":"Keming Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keming Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103090910","display_name":"Yaojie Lu","orcid":"https://orcid.org/0000-0002-5842-7715"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaojie Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620300","display_name":"Xianpei Han","orcid":"https://orcid.org/0000-0002-1304-6302"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianpei Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109888639","display_name":"Ben He","orcid":"https://orcid.org/0000-0002-2699-9209"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034536222","display_name":"Le Sun","orcid":"https://orcid.org/0000-0002-4221-0327"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jingren Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingren Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Junyang Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junyang Lin","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":"9073","last_page":"9085"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9627000093460083,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9627000093460083,"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/T10028","display_name":"Topic Modeling","score":0.9144999980926514,"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/T12031","display_name":"Speech and dialogue systems","score":0.9133999943733215,"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":0.6601824164390564},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5684635043144226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33650118112564087},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15260478854179382},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0756954550743103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6601824164390564},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5684635043144226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33650118112564087},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15260478854179382},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0756954550743103}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.473","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.473","pdf_url":"https://aclanthology.org/2025.findings-acl.473.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.473","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.473","pdf_url":"https://aclanthology.org/2025.findings-acl.473.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/G7398645837","display_name":null,"funder_award_id":"62272439","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888469.pdf","grobid_xml":"https://content.openalex.org/works/W4412888469.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":{"The":[0],"key":[1],"to":[2,41,53,83,96],"effective":[3],"alignment":[4,19,132,151],"lies":[5],"in":[6,129,149],"highquality":[7,71],"preference":[8,72,131,144],"data.Recent":[9],"research":[10,26],"has":[11,27,38],"focused":[12,29],"on":[13,30,108],"automated":[14,150],"alignment,":[15],"which":[16,45,93],"involves":[17],"developing":[18,31],"systems":[20],"with":[21],"minimal":[22],"human":[23,130],"intervention.However,":[24],"prior":[25],"predominantly":[28],"data":[32,86],"generation":[33],"methods,":[34],"while":[35],"insufficient":[36],"attention":[37],"been":[39],"paid":[40],"quality":[42],"control":[43],"mechanisms,":[44],"often":[46],"produce":[47,97],"inaccurate":[48],"and":[49,99,115,133],"unhelpful":[50],"data,":[51,73],"leading":[52],"unpredictable":[54],"benefits":[55],"during":[56],"iterative":[57],"optimization.In":[58],"this":[59],"paper,":[60],"we":[61],"present":[62],"Self-Steering":[63],"Optimization":[64],"(SSO),":[65],"an":[66],"algorithm":[67],"that":[68,124],"autonomously":[69],"generates":[70],"eliminating":[74],"manual":[75],"annotation":[76],"requirements.SSO":[77],"employs":[78],"a":[79,85,140],"specialized":[80],"optimization":[81],"objective":[82],"build":[84],"generator":[87],"from":[88],"the":[89,147],"policy":[90],"model":[91],"itself,":[92],"is":[94],"used":[95],"accurate":[98],"on-policy":[100],"data.We":[101],"demonstrate":[102],"SSO's":[103],"effectiveness":[104],"through":[105],"comprehensive":[106],"experiments":[107],"two":[109],"series":[110],"of":[111],"models:":[112],"Llama":[113],"3":[114],"Qwen":[116],"2.":[117],"Our":[118],"evaluation":[119],"across":[120],"diverse":[121],"benchmarks":[122],"shows":[123],"SSO":[125,138],"consistently":[126],"outperforms":[127],"baselines":[128],"reward":[134],"optimization.Further":[135],"analysis":[136],"validates":[137],"as":[139],"scalable":[141],"framework":[142],"for":[143],"optimization,":[145],"benefiting":[146],"advancement":[148],"techniques.":[152]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}