{"id":"https://openalex.org/W4412944795","doi":"https://doi.org/10.18653/v1/2025.acl-long.1104","title":"S2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning","display_name":"S2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944795","doi":"https://doi.org/10.18653/v1/2025.acl-long.1104"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1104","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1104","pdf_url":null,"source":null,"license":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102851997","display_name":"Ruijuan Ma","orcid":"https://orcid.org/0000-0003-4045-3285"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruotian Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Peisong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peisong Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384275","display_name":"Cheng Liu","orcid":"https://orcid.org/0000-0001-8967-1174"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101688566","display_name":"Xingyan Liu","orcid":"https://orcid.org/0000-0001-5117-0606"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingyan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434197","display_name":"Jiaqi Chen","orcid":"https://orcid.org/0000-0002-4069-193X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaqi Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082907437","display_name":"Bang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112622347","display_name":"Xin Zhou","orcid":"https://orcid.org/0009-0001-9321-3632"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100721790","display_name":"Nan Du","orcid":"https://orcid.org/0000-0003-2855-7452"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nan Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100648221","display_name":"Jia Li","orcid":"https://orcid.org/0000-0002-1824-9379"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia 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":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22632","last_page":"22654"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.9520999789237976,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.9520999789237976,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6829149723052979},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6248979568481445},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5328382253646851},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4097749590873718},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17672225832939148},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12886488437652588}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6829149723052979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6248979568481445},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5328382253646851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4097749590873718},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17672225832939148},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12886488437652588}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1104","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1104","pdf_url":null,"source":null,"license":null,"license_id":null,"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":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}
