{"id":"https://openalex.org/W4412888638","doi":"https://doi.org/10.18653/v1/2025.findings-acl.333","title":"Probability-Consistent Preference Optimization for Enhanced LLM Reasoning","display_name":"Probability-Consistent Preference Optimization for Enhanced LLM Reasoning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888638","doi":"https://doi.org/10.18653/v1/2025.findings-acl.333"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.333","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.333","pdf_url":"https://aclanthology.org/2025.findings-acl.333.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.333.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000327506","display_name":"Yunqiao Yang","orcid":"https://orcid.org/0000-0003-0109-8903"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunqiao Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085999236","display_name":"Houxing Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Houxing Ren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064962047","display_name":"Zimu Lu","orcid":"https://orcid.org/0000-0001-8479-2807"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zimu Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100602055","display_name":"Ke Wang","orcid":"https://orcid.org/0000-0001-5354-793X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061386830","display_name":"Weikang Shi","orcid":"https://orcid.org/0000-0002-4068-1168"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weikang Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041431476","display_name":"Aojun Zhou","orcid":"https://orcid.org/0000-0002-4742-8624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aojun Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088732762","display_name":"Junting Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junting Pan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072763304","display_name":"Mingjie Zhan","orcid":"https://orcid.org/0000-0001-8221-9089"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingjie Zhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5114506692","display_name":"Hongsheng Li","orcid":"https://orcid.org/0009-0003-4821-5051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongsheng Li","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14416997,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6435","last_page":"6448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9498999714851379,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9498999714851379,"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.9262999892234802,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.90829998254776,"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/preference","display_name":"Preference","score":0.7010147571563721},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6113051176071167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3617880940437317},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.18030673265457153},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14597034454345703}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7010147571563721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6113051176071167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3617880940437317},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18030673265457153},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14597034454345703}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.333","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.333","pdf_url":"https://aclanthology.org/2025.findings-acl.333.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.333","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.333","pdf_url":"https://aclanthology.org/2025.findings-acl.333.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":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"},{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888638.pdf","grobid_xml":"https://content.openalex.org/works/W4412888638.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":{"Recent":[0],"advances":[1],"in":[2,14],"preference":[3,24,60],"optimization":[4],"have":[5],"demonstrated":[6],"significant":[7],"potential":[8],"for":[9,59],"improving":[10],"mathematical":[11],"reasoning":[12],"capabilities":[13],"large":[15],"language":[16],"models":[17],"(LLMs).While":[18],"current":[19],"approaches":[20,84],"leverage":[21],"high-quality":[22],"pairwise":[23],"data":[25],"through":[26],"outcome-based":[27],"criteria":[28],"like":[29],"answer":[30,64],"correctness":[31,65],"or":[32],"consistency,":[33],"they":[34],"fundamentally":[35],"neglect":[36],"the":[37],"internal":[38],"logical":[39],"coherence":[40],"of":[41,89],"responses.To":[42],"overcome":[43],"this,":[44],"we":[45],"propose":[46],"Probability-Consistent":[47],"Preference":[48],"Optimization":[49],"(PCPO),":[50],"a":[51,86],"novel":[52],"framework":[53],"that":[54,76],"establishes":[55],"dual":[56],"quantitative":[57],"metrics":[58],"selection:":[61],"(1)":[62],"surface-level":[63],"and":[66,91],"(2)":[67],"intrinsic":[68],"token-level":[69],"probability":[70],"consistency":[71],"across":[72,85],"responses.Extensive":[73],"experiments":[74],"show":[75],"our":[77],"PCPO":[78],"consistently":[79],"outperforms":[80],"existing":[81],"outcome-only":[82],"criterion":[83],"diverse":[87],"range":[88],"LLMs":[90],"benchmarks.Our":[92],"code":[93],"is":[94],"publicly":[95],"available":[96],"at":[97],"https://github.com/YunqiaoYang/PCPO.":[98]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}