{"id":"https://openalex.org/W4412887851","doi":"https://doi.org/10.18653/v1/2025.findings-acl.930","title":"Process-based Self-Rewarding Language Models","display_name":"Process-based Self-Rewarding Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887851","doi":"https://doi.org/10.18653/v1/2025.findings-acl.930"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.930","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.930","pdf_url":"https://aclanthology.org/2025.findings-acl.930.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.930.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113229263","display_name":"Shimao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shimao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441094","display_name":"Xiao Liu","orcid":"https://orcid.org/0000-0002-9226-4569"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027743278","display_name":"Xin Zhang","orcid":"https://orcid.org/0000-0002-1515-7145"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020216680","display_name":"Junxiao Liu","orcid":"https://orcid.org/0000-0001-7245-1685"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junxiao Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075367840","display_name":"Zheheng Luo","orcid":"https://orcid.org/0000-0001-8246-5511"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheheng Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103232189","display_name":"Shujian Huang","orcid":"https://orcid.org/0000-0002-1988-4809"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shujian Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041448669","display_name":"Yeyun Gong","orcid":"https://orcid.org/0000-0001-9954-9674"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yeyun Gong","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18097","last_page":"18110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.7261999845504761,"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":0.7261999845504761,"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/computer-science","display_name":"Computer science","score":0.6905949115753174},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.641751766204834},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33994126319885254},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3293154835700989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6905949115753174},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.641751766204834},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33994126319885254},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3293154835700989}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.930","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.930","pdf_url":"https://aclanthology.org/2025.findings-acl.930.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.930","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.930","pdf_url":"https://aclanthology.org/2025.findings-acl.930.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":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887851.pdf","grobid_xml":"https://content.openalex.org/works/W4412887851.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":{"Large":[0],"Language":[1],"Models":[2],"have":[3,12],"demonstrated":[4],"outstanding":[5],"performance":[6,105],"across":[7],"various":[8],"downstream":[9],"tasks":[10],"and":[11,66,92],"been":[13,43],"widely":[14],"applied":[15],"in":[16,62,73],"multiple":[17,109],"scenarios.Human-annotated":[18],"preference":[19,94],"data":[20,49],"is":[21,31,59],"used":[22],"for":[23,83],"training":[24,48],"to":[25,70,124],"further":[26],"improve":[27],"LLMs'":[28],"performance,":[29],"which":[30,86],"constrained":[32],"by":[33,50],"the":[34,55,79,97,104,118],"upper":[35],"limit":[36],"of":[37,106,121],"human":[38,131],"performance.Therefore,":[39],"Self-Rewarding":[40,81],"method":[41],"has":[42],"proposed,":[44],"where":[45],"LLMs":[46,107],"generate":[47],"rewarding":[51],"their":[52],"own":[53],"outputs.However,":[54],"existing":[56],"self-rewarding":[57,98,123],"paradigm":[58,101],"not":[60],"effective":[61],"mathematical":[63,110],"reasoning":[64,111,127],"scenarios":[65],"may":[67,129],"even":[68],"lead":[69],"a":[71],"decline":[72],"performance.In":[74],"this":[75],"work,":[76],"we":[77],"propose":[78],"Process-based":[80,115],"pipeline":[82],"language":[84],"models,":[85],"introduces":[87],"long-thought":[88],"reasoning,":[89],"stepwise":[90],"LLM-as-a-Judge,":[91],"step-wise":[93],"optimization":[95],"within":[96],"paradigm.Our":[99],"new":[100],"successfully":[102],"enhances":[103],"on":[108],"benchmarks":[112],"through":[113],"iterative":[114],"Self-Rewarding,":[116],"demonstrating":[117],"immense":[119],"potential":[120],"process-based":[122],"achieve":[125],"LLM":[126],"that":[128],"surpass":[130],"capabilities.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}