{"id":"https://openalex.org/W4412889765","doi":"https://doi.org/10.18653/v1/2025.acl-long.1448","title":"Theorem Prover as a Judge for Synthetic Data Generation","display_name":"Theorem Prover as a Judge for Synthetic Data Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889765","doi":"https://doi.org/10.18653/v1/2025.acl-long.1448"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1448","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1448","pdf_url":"https://aclanthology.org/2025.acl-long.1448.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.1448.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114335069","display_name":"Joshua Ong Jun Leang","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joshua Ong Jun Leang","raw_affiliation_strings":["School of Informatics , The University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics , The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101670489","display_name":"Giwon Hong","orcid":"https://orcid.org/0000-0001-5239-9189"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Giwon Hong","raw_affiliation_strings":["School of Informatics , The University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics , The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103813027","display_name":"Wenda Li","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenda Li","raw_affiliation_strings":["School of Informatics , The University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics , The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030503109","display_name":"Shay B. Cohen","orcid":"https://orcid.org/0000-0003-4753-8353"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shay B Cohen","raw_affiliation_strings":["School of Informatics , The University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics , The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":1.4079,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80846737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"29941","last_page":"29977"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.5867000222206116,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.5867000222206116,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.5812000036239624,"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/T10126","display_name":"Logic, programming, and type systems","score":0.5651999711990356,"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/gas-meter-prover","display_name":"Gas meter prover","score":0.6989795565605164},{"id":"https://openalex.org/keywords/automated-theorem-proving","display_name":"Automated theorem proving","score":0.6740504503250122},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6041054129600525},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4732259511947632},{"id":"https://openalex.org/keywords/calculus","display_name":"Calculus (dental)","score":0.41187530755996704},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36632072925567627},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32917520403862},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2639266550540924},{"id":"https://openalex.org/keywords/mathematical-proof","display_name":"Mathematical proof","score":0.0818612277507782},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.07624372839927673}],"concepts":[{"id":"https://openalex.org/C159718280","wikidata":"https://www.wikidata.org/wiki/Q5526353","display_name":"Gas meter prover","level":3,"score":0.6989795565605164},{"id":"https://openalex.org/C206880738","wikidata":"https://www.wikidata.org/wiki/Q431667","display_name":"Automated theorem proving","level":2,"score":0.6740504503250122},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6041054129600525},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4732259511947632},{"id":"https://openalex.org/C2777686260","wikidata":"https://www.wikidata.org/wiki/Q144037","display_name":"Calculus (dental)","level":2,"score":0.41187530755996704},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36632072925567627},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32917520403862},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2639266550540924},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.0818612277507782},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.07624372839927673},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C199343813","wikidata":"https://www.wikidata.org/wiki/Q12128","display_name":"Dentistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1448","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1448","pdf_url":"https://aclanthology.org/2025.acl-long.1448.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"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/d40621d2-10a8-4b74-9ccb-77be16ae7726","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/d40621d2-10a8-4b74-9ccb-77be16ae7726","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1448","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1448","pdf_url":"https://aclanthology.org/2025.acl-long.1448.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":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889765.pdf","grobid_xml":"https://content.openalex.org/works/W4412889765.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4406231568"],"related_works":["https://openalex.org/W4246350535","https://openalex.org/W4238632608","https://openalex.org/W3083050876","https://openalex.org/W1875958796","https://openalex.org/W1780472831","https://openalex.org/W1976200187","https://openalex.org/W1561644379","https://openalex.org/W2969536091","https://openalex.org/W783488073","https://openalex.org/W2584449131"],"abstract_inverted_index":{"The":[0],"demand":[1],"for":[2,157,162,168],"synthetic":[3,110],"data":[4,36,111],"in":[5,132],"mathematical":[6,17,50],"reasoning":[7,29],"has":[8],"increased":[9],"due":[10],"to":[11,14,65,79,100],"its":[12],"potential":[13],"enhance":[15],"the":[16,25,47,70,74],"capabilities":[18],"of":[19,27,49,96],"large":[20],"language":[21],"models":[22],"(LLMs).However,":[23],"ensuring":[24],"validity":[26],"intermediate":[28,104],"steps":[30],"remains":[31,52],"a":[32,88,91,122],"significant":[33],"challenge,":[34],"affecting":[35],"quality.While":[37],"formal":[38],"verification":[39],"via":[40],"theorem":[41,62,97,129],"provers":[42],"effectively":[43,106],"validates":[44],"LLM":[45,103],"reasoning,":[46,105],"autoformalisation":[48,108],"proofs":[51],"error-prone.We":[53],"introduce":[54,84],"iterative":[55],"autoformalisation,":[56],"an":[57],"approach":[58],"that":[59,93,124],"iteratively":[60],"refines":[61],"prover":[63,76,98,130],"formalisation":[64,99],"mitigate":[66],"errors,":[67],"thereby":[68],"increasing":[69],"execution":[71],"rate":[72],"on":[73,155,160,166],"Lean":[75],"from":[77,117,135],"60%":[78],"87%.Building":[80],"upon":[81],"that,":[82],"we":[83,113],"Theorem":[85,118],"Prover":[86,119],"as":[87],"Judge":[89],"(TP-as-a-Judge),":[90],"method":[92],"makes":[94],"use":[95],"rigorously":[101],"assess":[102],"integrating":[107],"with":[109,128,147],"generation.Finally,":[112],"present":[114],"Reinforcement":[115,133],"Learning":[116,134],"Feedback":[120,137],"(RLTPF),":[121],"framework":[123],"replaces":[125],"human":[126],"annotation":[127],"feedback":[131],"Human":[136],"(RLHF).Across":[138],"multiple":[139],"LLMs,":[140],"applying":[141],"TP-as-a-Judge":[142],"and":[143,164],"RLTPF":[144],"improves":[145],"benchmarks":[146],"only":[148],"3,508":[149],"samples,":[150],"achieving":[151],"5.56%":[152],"accuracy":[153],"gain":[154],"Mistral-7B":[156],"MultiArith,":[158],"6.00%":[159],"Llama-2-7B":[161],"SVAMP,":[163],"3.55%":[165],"Llama-3.1-8B":[167],"AQUA.":[169],"1":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}