{"id":"https://openalex.org/W4416033914","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1162","title":"Retrieval-Augmented Language Models are Mimetic Theorem Provers","display_name":"Retrieval-Augmented Language Models are Mimetic Theorem Provers","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033914","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1162"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1162","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1162","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1162.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: EMNLP 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-emnlp.1162.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108133522","display_name":"Wenjie Yang","orcid":"https://orcid.org/0000-0001-5420-2722"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjie Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112898797","display_name":"Ruiyuan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiyuan Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102413863","display_name":"Jiaxing Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxing Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zicheng Lyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zicheng Lyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108212854","display_name":"Tingting Xu","orcid":"https://orcid.org/0009-0000-5436-1475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tongshan Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086213157","display_name":"Shengzhong Zhang","orcid":"https://orcid.org/0000-0003-1783-6835"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengzhong Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052534353","display_name":"Liang Du","orcid":"https://orcid.org/0000-0002-2663-0751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lun Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101350111","display_name":"Da Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Da Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5062549536","display_name":"Zengfeng Huang","orcid":"https://orcid.org/0000-0003-2671-7483"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zengfeng Huang","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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21301","last_page":"21313"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.35910001397132874,"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/T10028","display_name":"Topic Modeling","score":0.35910001397132874,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.12160000205039978,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.09520000219345093,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/automated-theorem-proving","display_name":"Automated theorem proving","score":0.3781999945640564},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3517000079154968},{"id":"https://openalex.org/keywords/calculus","display_name":"Calculus (dental)","score":0.31450000405311584},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.2987000048160553},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2865000069141388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5268999934196472},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.41119998693466187},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.384799987077713},{"id":"https://openalex.org/C206880738","wikidata":"https://www.wikidata.org/wiki/Q431667","display_name":"Automated theorem proving","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35429999232292175},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34950000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33959999680519104},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3165000081062317},{"id":"https://openalex.org/C2777686260","wikidata":"https://www.wikidata.org/wiki/Q144037","display_name":"Calculus (dental)","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.31029999256134033},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1162","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1162","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1162.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1162","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1162","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1162.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416033914.pdf","grobid_xml":"https://content.openalex.org/works/W4416033914.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,38,180],"models":[2,56,181],"have":[3,192,211],"shown":[4],"impressive":[5],"capabilities":[6,203],"in":[7,124,162,204],"various":[8],"mathematical":[9,177,200],"tasks,":[10],"yet":[11,82],"they":[12],"often":[13],"struggle":[14],"with":[15,46,127,149],"rigorous,":[16,205],"proof-based":[17,206],"reasoning":[18,101,207],"required":[19],"for":[20,36,70],"research-level":[21,160],"mathematics.Retrieval-augmented":[22],"generation":[23],"presents":[24],"a":[25,80,171,175,197],"promising":[26],"path":[27],"to":[28,66,97,112,131,158],"address":[29],"this":[30,74],"limitation.This":[31],"paper":[32],"systematically":[33],"explores":[34],"RAG":[35,84,94,120,154],"natural":[37],"theorem":[39,54],"proving.We":[40],"reveal":[41],"that":[42,86,118,136],"LLMs,":[43],"when":[44,147],"augmented":[45],"retrieved":[47,64],"proofs,":[48],"can":[49,57],"function":[50],"as":[51,170,184],"powerful":[52],"mimetic":[53],"provers:":[55],"effectively":[58],"generalize":[59],"proof":[60,92,145],"techniques":[61],"from":[62],"unstructured":[63],"contexts":[65,111],"construct":[67],"correct":[68],"proofs":[69],"novel":[71],"theorems.Building":[72],"upon":[73],"insight,":[75],"we":[76],"introduce":[77],"Dual":[78,119,153],"RAG,":[79],"simple":[81],"effective":[83],"framework":[85],"retrieves":[87],"both":[88,107],"relevant":[89],"theorems":[90,161],"and":[91,109,188],"techniques.Dual":[93],"uses":[95],"LLMs":[96],"identify":[98],"the":[99,150,156],"underlying":[100],"challenges":[102],"posed":[103],"by":[104],"theorems,":[105],"enhancing":[106],"queries":[108],"document":[110],"improve":[113],"retrieval":[114,125,138],"quality.Our":[115],"experiments":[116],"show":[117],"achieves":[121],"substantial":[122,213],"improvements":[123],"performance,":[126],"gains":[128],"of":[129,174,199],"up":[130],"34.19%.Expert":[132],"evaluations":[133],"further":[134],"confirm":[135],"these":[137],"enhancements":[139],"directly":[140],"translate":[141],"into":[142],"higher":[143],"quality":[144],"generation.Notably,":[146],"integrated":[148],"arXiv":[151],"API,":[152],"demonstrates":[155],"ability":[157],"prove":[159],"theoretical":[163],"machine":[164],"learning,":[165],"highlighting":[166],"its":[167],"strong":[168,194],"potential":[169],"foundational":[172],"element":[173],"practical":[176],"copilot.Recent":[178],"large":[179],"(LLMs),":[182],"such":[183],"OpenAI-o1":[185],"(OpenAI,":[186],"2024)":[187],"DeepSeek-R1":[189],"(DeepSeek-AI,":[190],"2025),":[191],"demonstrated":[193],"performance":[195],"on":[196],"variety":[198],"benchmarks.However,":[201],"their":[202],"remain":[208],"underexplored.Early":[209],"studies":[210],"revealed":[212],"limitations":[214]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}