{"id":"https://openalex.org/W4412886711","doi":"https://doi.org/10.18653/v1/2025.acl-long.216","title":"An Efficient and Precise Training Data Construction Framework for Process-supervised Reward Model in Mathematical Reasoning","display_name":"An Efficient and Precise Training Data Construction Framework for Process-supervised Reward Model in Mathematical Reasoning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886711","doi":"https://doi.org/10.18653/v1/2025.acl-long.216"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.216","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.216","pdf_url":"https://aclanthology.org/2025.acl-long.216.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":"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":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.216.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059618326","display_name":"Wei Sun","orcid":"https://orcid.org/0000-0002-6705-1326"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065361815","display_name":"Qianlong Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qianlong Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002237594","display_name":"Fuwei Cui","orcid":"https://orcid.org/0000-0001-6800-3791"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fuwei Cui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5104095863","display_name":"Jiajun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiajun Zhang","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":0.21478184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4292","last_page":"4305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14484","display_name":"Technology and Data Analysis","score":0.5006999969482422,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T14484","display_name":"Technology and Data Analysis","score":0.5006999969482422,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.462799996137619,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.44850000739097595,"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/computer-science","display_name":"Computer science","score":0.7690346240997314},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.7041462063789368},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.615205705165863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6035380363464355},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.556179940700531},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.4941003620624542},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4867880046367645},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.4326876401901245},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.13950932025909424},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.11273595690727234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7690346240997314},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.7041462063789368},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.615205705165863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6035380363464355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.556179940700531},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.4941003620624542},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4867880046367645},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.4326876401901245},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.13950932025909424},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.11273595690727234},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.216","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.216","pdf_url":"https://aclanthology.org/2025.acl-long.216.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.216","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.216","pdf_url":"https://aclanthology.org/2025.acl-long.216.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886711.pdf","grobid_xml":"https://content.openalex.org/works/W4412886711.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1488241869","https://openalex.org/W2351118185","https://openalex.org/W94330105","https://openalex.org/W2361142061","https://openalex.org/W2314311764","https://openalex.org/W2574333357","https://openalex.org/W2087772460","https://openalex.org/W2077968118","https://openalex.org/W2347305376","https://openalex.org/W646848429"],"abstract_inverted_index":{"Enhancing":[0],"the":[1,25,30,121],"mathematical":[2],"reasoning":[3,26,32,76],"capabilities":[4],"of":[5,11,111],"Large":[6],"Language":[7],"Models":[8],"(LLMs)":[9],"is":[10],"great":[12],"scientific":[13],"and":[14,46,83,95],"practical":[15],"significance.Researchers":[16],"typically":[17],"employ":[18],"process-supervised":[19],"reward":[20],"models":[21],"(PRMs)":[22],"to":[23,90,116],"guide":[24],"process,":[27],"effectively":[28],"improving":[29],"models'":[31],"abilities.However,":[33],"existing":[34],"methods":[35],"for":[36],"constructing":[37],"process":[38,104],"supervision":[39,105],"training":[40,106],"data,":[41],"such":[42],"as":[43],"manual":[44],"annotation":[45,93],"perstep":[47],"Monte":[48],"Carlo":[49],"estimation,":[50],"are":[51],"often":[52],"costly":[53],"or":[54],"suffer":[55],"from":[56],"poor":[57],"quality.To":[58],"address":[59],"these":[60],"challenges,":[61],"this":[62,97],"paper":[63],"introduces":[64],"a":[65,102],"framework":[66],"called":[67],"EpicPRM":[68],"(Efficient,":[69],"Precise,":[70],"Cheap),":[71],"which":[72],"annotates":[73],"each":[74],"intermediate":[75,114],"step":[77],"based":[78],"on":[79,124],"its":[80],"quantified":[81],"contribution":[82],"uses":[84],"an":[85],"adaptive":[86],"binary":[87],"search":[88],"algorithm":[89],"enhance":[91],"both":[92],"precision":[94],"efficiency.Using":[96],"approach,":[98],"we":[99],"efficiently":[100],"construct":[101],"high-quality":[103],"dataset":[107],"named":[108],"Epic50k,":[109],"consisting":[110],"50k":[112],"annotated":[113],"steps.Compared":[115],"other":[117],"publicly":[118],"available":[119],"datasets,":[120],"PRM":[122],"trained":[123],"Epic50k":[125,130],"demonstrates":[126],"significantly":[127],"superior":[128],"performance.Getting":[129],"at":[131],"https://github.com/xiaolizh1/EpicPRM.":[132]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}