{"id":"https://openalex.org/W4412888562","doi":"https://doi.org/10.18653/v1/2025.findings-acl.547","title":"The Lessons of Developing Process Reward Models in Mathematical Reasoning","display_name":"The Lessons of Developing Process Reward Models in Mathematical Reasoning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888562","doi":"https://doi.org/10.18653/v1/2025.findings-acl.547"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.547","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.547","pdf_url":"https://aclanthology.org/2025.findings-acl.547.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.547.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045476473","display_name":"Zhenru Zhang","orcid":"https://orcid.org/0009-0009-0553-3491"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhenru Zhang","raw_affiliation_strings":["Qwen Team , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Team , Alibaba Group","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016924921","display_name":"Chujie Zheng","orcid":"https://orcid.org/0000-0002-7364-972X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Chujie Zheng","raw_affiliation_strings":["Qwen Team , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Team , Alibaba Group","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110596451","display_name":"Yangzhen Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yangzhen Wu","raw_affiliation_strings":["Qwen Team , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Team , Alibaba Group","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101849101","display_name":"Beichen Zhang","orcid":"https://orcid.org/0000-0001-9378-0250"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Beichen Zhang","raw_affiliation_strings":["Qwen Team , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Team , Alibaba Group","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003991609","display_name":"Runji Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Runji Lin","raw_affiliation_strings":["Qwen Team , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Team , Alibaba Group","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109790389","display_name":"B. X. Yu","orcid":"https://orcid.org/0009-0004-6964-9083"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Bowen Yu","raw_affiliation_strings":["Qwen Team , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Team , Alibaba Group","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062188134","display_name":"Dayiheng Liu","orcid":"https://orcid.org/0000-0002-8755-8941"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Dayiheng Liu","raw_affiliation_strings":["Qwen Team , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Team , Alibaba Group","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057864403","display_name":"Jingren Zhou","orcid":"https://orcid.org/0000-0002-4220-2634"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jingren Zhou","raw_affiliation_strings":["Qwen Team , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Team , Alibaba Group","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100612233","display_name":"Junyang Lin","orcid":"https://orcid.org/0000-0001-9931-383X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Junyang Lin","raw_affiliation_strings":["Qwen Team , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Team , Alibaba Group","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.0702,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.98667972,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10495","last_page":"10516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12805","display_name":"Cognitive Science and Mapping","score":0.5577999949455261,"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/T12805","display_name":"Cognitive Science and Mapping","score":0.5577999949455261,"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/T11810","display_name":"Complex Systems and Decision Making","score":0.4796000123023987,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.699394166469574},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6421583890914917},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.34245792031288147},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12730944156646729},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11566677689552307}],"concepts":[{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.699394166469574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6421583890914917},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.34245792031288147},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12730944156646729},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11566677689552307}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.547","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.547","pdf_url":"https://aclanthology.org/2025.findings-acl.547.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.547","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.547","pdf_url":"https://aclanthology.org/2025.findings-acl.547.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/W4412888562.pdf","grobid_xml":"https://content.openalex.org/works/W4412888562.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":{"Process":[0],"Reward":[1],"Models":[2,21],"(PRMs)":[3],"aim":[4],"to":[5,63],"identify":[6,70],"and":[7,35,60,65,97,107,119,126,143],"mitigate":[8],"intermediate":[9],"errors":[10],"in":[11,15,32,73,122],"the":[12,23,111,123,127],"reasoning":[13,17],"processes":[14],"mathematical":[16],"of":[18,25],"Large":[19],"Language":[20],"(LLMs).However,":[22],"development":[24],"effective":[26],"PRMs":[27,55],"faces":[28],"significant":[29],"challenges,":[30,83],"particularly":[31],"data":[33,52,120],"annotation":[34,67],"evaluation":[36,77,102,125],"methodologies.In":[37],"this":[38],"paper,":[39],"through":[40],"extensive":[41],"experiments,":[42],"we":[43,69,84,113,132],"demonstrate":[44],"that":[45,90,104,138],"commonly":[46],"used":[47],"Monte":[48],"Carlo":[49],"(MC)":[50],"estimation-based":[51],"synthesis":[53],"for":[54,79,147],"typically":[56],"yields":[57],"inferior":[58],"performance":[59,118],"generalization":[61],"compared":[62],"LLM-as-a-judge":[64,96],"human":[66],"methods.Furthermore,":[68],"potential":[71],"biases":[72],"conventional":[74],"Bestof-N":[75],"(BoN)":[76],"strategies":[78],"PRMs.To":[80],"address":[81],"these":[82],"develop":[85],"a":[86,99,134],"consensus":[87],"filtering":[88],"mechanism":[89],"effectively":[91],"integrates":[92],"MC":[93],"estimation":[94],"with":[95],"advocates":[98],"more":[100],"comprehensive":[101],"framework":[103],"combines":[105],"response-level":[106],"step-level":[108],"metrics.Based":[109],"on":[110],"mechanisms,":[112],"significantly":[114],"improve":[115],"both":[116],"model":[117],"efficiency":[121],"BoN":[124],"step-wise":[128],"error":[129],"identification":[130],"task.Finally,":[131],"release":[133],"new":[135],"state-of-the-art":[136],"PRM":[137],"outperforms":[139],"existing":[140],"open-source":[141],"alternatives":[142],"provides":[144],"practical":[145],"guidelines":[146],"future":[148],"research.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
