{"id":"https://openalex.org/W4394780874","doi":"https://doi.org/10.48550/arxiv.2404.07382","title":"Learn from Failure: Fine-Tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving","display_name":"Learn from Failure: Fine-Tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving","publication_year":2024,"publication_date":"2024-04-10","ids":{"openalex":"https://openalex.org/W4394780874","doi":"https://doi.org/10.48550/arxiv.2404.07382"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2404.07382","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.07382","pdf_url":"https://arxiv.org/pdf/2404.07382","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":null},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.07382","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102648310","display_name":"Chenyang An","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"An, Chenyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079572598","display_name":"Zhibo Chen","orcid":"https://orcid.org/0000-0002-8525-5066"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhibo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113391955","display_name":"Q Ye","orcid":"https://orcid.org/0009-0000-7980-237X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Qihao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102852428","display_name":"Emily First","orcid":"https://orcid.org/0000-0002-2896-2928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"First, Emily","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001458884","display_name":"Letian Peng","orcid":"https://orcid.org/0000-0001-5039-3496"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Letian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037854753","display_name":"Jiayun Zhang","orcid":"https://orcid.org/0000-0002-3562-5794"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiayun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038338582","display_name":"Zihan Wang","orcid":"https://orcid.org/0000-0002-3147-4642"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zihan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043665959","display_name":"Sorin Lerner","orcid":"https://orcid.org/0000-0003-3957-0628"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lerner, Sorin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5039500313","display_name":"Jingbo Shang","orcid":"https://orcid.org/0000-0002-7249-4404"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shang, Jingbo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5102648310"],"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/T10260","display_name":"Software Engineering Research","score":0.9944999814033508,"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/T10260","display_name":"Software Engineering Research","score":0.9944999814033508,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9882000088691711,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9876000285148621,"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/correctness","display_name":"Correctness","score":0.7916148900985718},{"id":"https://openalex.org/keywords/mathematical-proof","display_name":"Mathematical proof","score":0.7233006954193115},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6354305744171143},{"id":"https://openalex.org/keywords/automated-theorem-proving","display_name":"Automated theorem proving","score":0.5268827080726624},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4770571291446686},{"id":"https://openalex.org/keywords/propositional-calculus","display_name":"Propositional calculus","score":0.4596201479434967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43736135959625244},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.40552669763565063},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33574825525283813},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3156653046607971},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24924716353416443},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23215848207473755}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7916148900985718},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.7233006954193115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6354305744171143},{"id":"https://openalex.org/C206880738","wikidata":"https://www.wikidata.org/wiki/Q431667","display_name":"Automated theorem proving","level":2,"score":0.5268827080726624},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4770571291446686},{"id":"https://openalex.org/C69562738","wikidata":"https://www.wikidata.org/wiki/Q200694","display_name":"Propositional calculus","level":2,"score":0.4596201479434967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43736135959625244},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40552669763565063},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33574825525283813},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3156653046607971},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24924716353416443},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23215848207473755},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2404.07382","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.07382","pdf_url":"https://arxiv.org/pdf/2404.07382","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":null},{"id":"doi:10.48550/arxiv.2404.07382","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2404.07382","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2404.07382","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.07382","pdf_url":"https://arxiv.org/pdf/2404.07382","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":null},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2625870048","display_name":"SHF: Medium: Generating Correctness Proofs with Neural Networks","funder_award_id":"1955457","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4463929942","display_name":"Collaborative Research: SHF: Small: Data-Driven Lemma Synthesis for Interactive Proofs","funder_award_id":"2220892","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394780874.pdf","grobid_xml":"https://content.openalex.org/works/W4394780874.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W2018477250","https://openalex.org/W55831818","https://openalex.org/W2624478615","https://openalex.org/W4297811169","https://openalex.org/W2606974619","https://openalex.org/W3100311625","https://openalex.org/W1937494301"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,117,134],"Automated":[3],"Theorem":[4],"Proving":[5],"have":[6],"shown":[7],"the":[8,41,90,98,111,142,162,168],"effectiveness":[9],"of":[10,100,113,144],"leveraging":[11],"a":[12,38,71,76,124],"(large)":[13],"language":[14],"model":[15,149],"that":[16,73,82,103,137,167],"generates":[17],"tactics":[18,51,84],"(i.e.":[19],"proof":[20,25,35,54],"steps)":[21],"to":[22,75],"search":[23,78,108],"through":[24],"states.":[26],"The":[27],"current":[28],"model,":[29],"while":[30],"trained":[31,150,159],"solely":[32],"on":[33,126,151,161],"successful":[34],"paths,":[36],"faces":[37],"discrepancy":[39],"at":[40,52],"inference":[42],"stage,":[43],"as":[44],"it":[45,133],"must":[46],"sample":[47],"and":[48,131,165],"try":[49],"various":[50],"each":[53],"state":[55],"until":[56],"finding":[57],"success,":[58],"unlike":[59],"its":[60],"training":[61,101],"which":[62],"does":[63],"not":[64],"incorporate":[65],"learning":[66],"from":[67,106],"failed":[68,77,107],"attempts.":[69],"Intuitively,":[70],"tactic":[72],"leads":[74],"path":[79],"would":[80],"indicate":[81],"similar":[83],"should":[85],"receive":[86],"less":[87],"attention":[88],"during":[89],"following":[91],"trials.":[92],"In":[93],"this":[94],"paper,":[95],"we":[96,122,138],"demonstrate":[97],"benefit":[99],"models":[102,158],"additionally":[104],"learn":[105],"paths.":[109],"Facing":[110],"lack":[112],"such":[114,136],"trial-and-error":[115,154],"data":[116],"existing":[118],"open-source":[119],"theorem-proving":[120],"datasets,":[121],"curate":[123],"dataset":[125],"intuitionistic":[127],"propositional":[128],"logic":[129],"theorems":[130,173],"formalize":[132],"Lean,":[135],"can":[139],"reliably":[140],"check":[141],"correctness":[143],"proofs.":[145],"We":[146],"compare":[147],"our":[148],"relatively":[152],"short":[153],"information":[155],"(TrialMaster)":[156],"with":[157,174],"only":[160],"correct":[163],"paths":[164],"discover":[166],"former":[169],"solves":[170],"more":[171],"unseen":[172],"lower":[175],"trial":[176],"searches.":[177]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}