{"id":"https://openalex.org/W4416611723","doi":"https://doi.org/10.48550/arxiv.2505.23486","title":"Autoformalization in the Era of Large Language Models: A Survey","display_name":"Autoformalization in the Era of Large Language Models: A Survey","publication_year":2025,"publication_date":"2025-05-29","ids":{"openalex":"https://openalex.org/W4416611723","doi":"https://doi.org/10.48550/arxiv.2505.23486"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.23486","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.23486","pdf_url":"https://arxiv.org/pdf/2505.23486","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.23486","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121177662","display_name":"Ke Weng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weng, Ke","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008387608","display_name":"Lun Du","orcid":"https://orcid.org/0000-0002-7625-0650","observed_orcids":["https://orcid.org/0000-0002-7625-0650"]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Du, Lun","raw_affiliation_strings":["Ant Research Institute , Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Research Institute , Ant Group","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121175449","display_name":"Sirui Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Sirui","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121141460","display_name":"Wangyue Lu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu, Wangyue","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104031673","display_name":"Haozhe Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sun, Haozhe","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030080621","display_name":"Hengyu Liu","orcid":"https://orcid.org/0000-0001-6545-7181","observed_orcids":["https://orcid.org/0000-0001-6545-7181","https://orcid.org/0009-0003-5557-0166"]},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Liu, Hengyu","raw_affiliation_strings":["Department of Computer Science , Aalborg University {2401925 , 20226504 , 2410827 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Aalborg University {2401925 , 20226504 , 2410827 ,","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121209152","display_name":"Tiancheng Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Tiancheng","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.7592999935150146,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.7592999935150146,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.12039999663829803,"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/T10028","display_name":"Topic Modeling","score":0.02850000001490116,"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/autoformalization","display_name":"autoformalization","score":0.9980000257492065},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8889999985694885},{"id":"https://openalex.org/keywords/formal-verification","display_name":"formal verification","score":0.7089999914169312},{"id":"https://openalex.org/keywords/automated-theorem-proving","display_name":"automated theorem proving","score":0.875},{"id":"https://openalex.org/keywords/mathematical-reasoning","display_name":"mathematical reasoning","score":0.5550000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.669700026512146},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6284000277519226},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5394999980926514},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5268999934196472},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.499099999666214},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4803999960422516},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.4652999937534332},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.4284000098705292},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3562999963760376},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.2971000075340271},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.2678999900817871}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2505.23486","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.23486","pdf_url":"https://arxiv.org/pdf/2505.23486","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:openaire/16c53a48-a14f-4c49-b978-84c410397bcb","doi":null,"is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/16c53a48-a14f-4c49-b978-84c410397bcb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Weng, K, Du, L, Li, S, Lu, W, Sun, H, Liu, H & Zhang, T 2025 'Autoformalization in the Era of Large Language Models : A Survey' arXiv. https://doi.org/10.48550/arXiv.2505.23486","raw_type":"info:eu-repo/semantics/preprint"},{"id":"doi:10.48550/arxiv.2505.23486","doi":"https://doi.org/10.48550/arxiv.2505.23486","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.23486","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.23486","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.23486","pdf_url":"https://arxiv.org/pdf/2505.23486","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416611723.pdf","grobid_xml":"https://content.openalex.org/works/W4416611723.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7166868666","https://openalex.org/W4282045675","https://openalex.org/W4415797512","https://openalex.org/W6979330430","https://openalex.org/W7081695718","https://openalex.org/W4399597224","https://openalex.org/W7111935609","https://openalex.org/W4415032442","https://openalex.org/W4416037116","https://openalex.org/W4414945653"],"abstract_inverted_index":{"Autoformalization,":[0],"the":[1,25,37,96,110,117,128,155],"process":[2],"of":[3,27,69,92,113,119,133],"transforming":[4],"informal":[5],"mathematical":[6,76,88],"propositions":[7],"into":[8],"verifiable":[9],"formal":[10],"representations,":[11],"is":[12,84],"a":[13,21,66],"foundational":[14],"task":[15],"in":[16,29,40,72,115],"automated":[17],"theorem":[18],"proving,":[19],"offering":[20],"new":[22,56],"perspective":[23],"on":[24],"use":[26],"mathematics":[28],"both":[30,55,75,127],"theoretical":[31],"and":[32,58,77,90,94,105,130,141,146,150],"applied":[33,85],"domains.":[34],"Driven":[35],"by":[36],"rapid":[38],"progress":[39],"artificial":[41],"intelligence,":[42],"particularly":[43],"large":[44],"language":[45],"models":[46,140],"(LLMs),":[47],"this":[48,62],"field":[49],"has":[50],"witnessed":[51],"substantial":[52],"growth,":[53],"bringing":[54],"opportunities":[57],"unique":[59],"challenges.":[60],"In":[61],"survey,":[63],"we":[64,136],"provide":[65],"comprehensive":[67],"overview":[68],"recent":[70],"advances":[71],"autoformalization":[73,83,114],"from":[74,99],"LLM-centric":[78],"perspectives.":[79],"We":[80,107],"examine":[81],"how":[82],"across":[86],"various":[87],"domains":[89],"levels":[91],"difficulty,":[93],"analyze":[95],"end-to-end":[97],"workflow":[98],"data":[100],"preprocessing":[101],"to":[102,125],"model":[103],"design":[104],"evaluation.":[106],"further":[108],"explore":[109],"emerging":[111],"role":[112],"enhancing":[116],"verifiability":[118],"LLM-generated":[120],"outputs,":[121],"highlighting":[122],"its":[123],"potential":[124],"improve":[126],"trustworthiness":[129],"reasoning":[131],"capabilities":[132],"LLMs.":[134],"Finally,":[135],"summarize":[137],"key":[138],"open-source":[139],"datasets":[142],"supporting":[143],"current":[144],"research,":[145],"discuss":[147],"open":[148],"challenges":[149],"promising":[151],"future":[152],"directions":[153],"for":[154],"field.":[156]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}
