{"id":"https://openalex.org/W4412888526","doi":"https://doi.org/10.18653/v1/2025.findings-acl.463","title":"Supervised Optimism Correction: Be Confident When LLMs Are Sure","display_name":"Supervised Optimism Correction: Be Confident When LLMs Are Sure","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888526","doi":"https://doi.org/10.18653/v1/2025.findings-acl.463"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.463","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.463","pdf_url":"https://aclanthology.org/2025.findings-acl.463.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.463.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108946894","display_name":"Junjie Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junjie Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113231897","display_name":"Rushuai Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rushuai Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090854835","display_name":"Shunyu Liu","orcid":"https://orcid.org/0000-0003-0584-9129"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shunyu Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069007219","display_name":"Ting-En Lin","orcid":"https://orcid.org/0000-0003-0650-7286"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ting-En Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042950753","display_name":"Fei Huang","orcid":"https://orcid.org/0000-0002-3805-8107"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100419239","display_name":"Yi Chen","orcid":"https://orcid.org/0000-0002-2225-690X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100644428","display_name":"Yongbin Li","orcid":"https://orcid.org/0009-0008-4504-2163"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongbin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dacheng Tao","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":"8867","last_page":"8880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10391","display_name":"Healthcare Policy and Management","score":0.8651999831199646,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10391","display_name":"Healthcare Policy and Management","score":0.8651999831199646,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/optimism","display_name":"Optimism","score":0.7866487503051758},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4449783265590668},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3376416862010956},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.23298794031143188}],"concepts":[{"id":"https://openalex.org/C204017024","wikidata":"https://www.wikidata.org/wiki/Q485446","display_name":"Optimism","level":2,"score":0.7866487503051758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4449783265590668},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3376416862010956},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.23298794031143188}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.463","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.463","pdf_url":"https://aclanthology.org/2025.findings-acl.463.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.463","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.463","pdf_url":"https://aclanthology.org/2025.findings-acl.463.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/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888526.pdf","grobid_xml":"https://content.openalex.org/works/W4412888526.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/W2122713011","https://openalex.org/W2071729956","https://openalex.org/W2900331548","https://openalex.org/W2965399423","https://openalex.org/W2116758642","https://openalex.org/W4247284515","https://openalex.org/W3141834514"],"abstract_inverted_index":{"In":[0],"this":[1,34,65],"work,":[2],"we":[3,37,67],"establish":[4],"a":[5,75,130],"novel":[6],"theoretical":[7,35],"connection":[8],"between":[9],"supervised":[10,86,107],"fine-tuning":[11],"and":[12,117],"offline":[13],"reinforcement":[14],"learning":[15],"under":[16],"the":[17,40,88,120,123],"tokenlevel":[18],"Markov":[19],"decision":[20],"process,":[21],"revealing":[22],"that":[23,39],"large":[24],"language":[25],"models":[26],"indeed":[27],"learn":[28],"an":[29],"implicit":[30,92],"Q-function":[31],"for":[32,81],"inference.Through":[33],"lens,":[36],"demonstrate":[38],"widely":[41],"used":[42],"beam":[43,127],"search":[44,128],"method":[45],"suffers":[46],"from":[47],"unacceptable":[48],"over-optimism,":[49],"where":[50],"inference":[51],"errors":[52],"are":[53],"inevitably":[54],"amplified":[55],"due":[56],"to":[57,95],"inflated":[58],"Q-value":[59],"estimations":[60,84],"of":[61,122,132],"suboptimal":[62],"steps.To":[63],"address":[64],"limitation,":[66],"propose":[68],"Supervised":[69],"Optimism":[70],"Correction":[71],"(SOC),":[72],"which":[73],"introduces":[74],"simple":[76],"yet":[77],"effective":[78],"auxiliary":[79,89],"loss":[80,90],"token-level":[82],"Qvalue":[83],"during":[85],"fine-tuning.Specifically,":[87],"employs":[91],"value":[93],"regularization":[94],"boost":[96],"model":[97],"confidence":[98],"in":[99],"expert-demonstrated":[100],"responses,":[101],"thereby":[102],"suppressing":[103],"over-optimism":[104],"toward":[105],"insufficiently":[106],"responses.Extensive":[108],"experiments":[109],"on":[110],"mathematical":[111],"reasoning":[112],"benchmarks,":[113],"including":[114],"GSM8K,":[115],"MATH,":[116],"GAOKAO,":[118],"showcase":[119],"superiority":[121],"proposed":[124],"SOC":[125],"with":[126],"across":[129],"series":[131],"open-source":[133],"models.":[134]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}