{"id":"https://openalex.org/W7168341900","doi":"https://doi.org/10.48448/xe1h-m056","title":"Reliable Use of Lemmas via Eligibility Reasoning and Section\u2011Aware Reinforcement Learning","display_name":"Reliable Use of Lemmas via Eligibility Reasoning and Section\u2011Aware Reinforcement Learning","publication_year":2026,"publication_date":"2026-06-03","ids":{"openalex":"https://openalex.org/W7168341900","doi":"https://doi.org/10.48448/xe1h-m056"},"language":"en","primary_location":{"id":"doi:10.48448/xe1h-m056","doi":"https://doi.org/10.48448/xe1h-m056","is_oa":true,"landing_page_url":"https://doi.org/10.48448/xe1h-m056","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"},"volume":null,"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/xe1h-m056","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140798803","display_name":"Association for Computational Linguistics 2026","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Association for Computational Linguistics 2026","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140967021","display_name":"Hao Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139812992","display_name":"Zicheng Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zicheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129699313","display_name":"Jiang Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016934680","display_name":"Ximeng Sun","orcid":"https://orcid.org/0000-0003-2187-0657","observed_orcids":["https://orcid.org/0000-0003-2187-0657"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Ximeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124880403","display_name":"Ze Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115829690","display_name":"Jialian Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jialian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133083513","display_name":"Zhikun Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu, Zhikun","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140834690","display_name":"Xiaodong Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu, Xiaodong","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137686113","display_name":"Ben Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Ben","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T10028","display_name":"Topic Modeling","score":0.45579999685287476,"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":0.45579999685287476,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.27639999985694885,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.08980000019073486,"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/large-language-models","display_name":"large language models","score":0.7450000047683716},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"structured prediction","score":0.7680000066757202},{"id":"https://openalex.org/keywords/formal-proof","display_name":"formal proof","score":0.4339999854564667},{"id":"https://openalex.org/keywords/mathematical-reasoning","display_name":"mathematical reasoning","score":0.7799999713897705},{"id":"https://openalex.org/keywords/robustness-to-disturbances","display_name":"robustness to disturbances","score":0.753000020980835}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8216999769210815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7023000121116638},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5996000170707703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46560001373291016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39340001344680786},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C2777026412","wikidata":"https://www.wikidata.org/wiki/Q2684591","display_name":"Statement (logic)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C192465680","wikidata":"https://www.wikidata.org/wiki/Q1413450","display_name":"Precondition","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.26460000872612},{"id":"https://openalex.org/C2777151079","wikidata":"https://www.wikidata.org/wiki/Q141160","display_name":"Parity (physics)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/xe1h-m056","doi":"https://doi.org/10.48448/xe1h-m056","is_oa":true,"landing_page_url":"https://doi.org/10.48448/xe1h-m056","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/xe1h-m056","doi":"https://doi.org/10.48448/xe1h-m056","is_oa":true,"landing_page_url":"https://doi.org/10.48448/xe1h-m056","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4387725649","https://openalex.org/W7133220068","https://openalex.org/W4407571385","https://openalex.org/W4416033826","https://openalex.org/W6948275686","https://openalex.org/W4416615461","https://openalex.org/W7212321358","https://openalex.org/W7106708571","https://openalex.org/W4417531489","https://openalex.org/W7219090560"],"abstract_inverted_index":{"Recent":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"perform":[5],"strongly":[6],"on":[7,85,129,137],"mathematical":[8],"benchmarks":[9],"yet":[10],"often":[11],"misapply":[12],"lemmas,":[13],"importing":[14],"conclusions":[15],"without":[16],"validating":[17],"assumptions.":[18],"We":[19,52],"formalize":[20],"lemma\u2011judging":[21],"as":[22],"a":[23,28,31,38,42,47,60,96,119,123],"structured":[24],"prediction":[25],"task:":[26],"given":[27],"statement":[29],"and":[30,41,63,82,88,100,106,122,132,146],"candidate":[32],"lemma,":[33],"the":[34,76,143],"model":[35,121],"must":[36],"output":[37,62],"precondition":[39],"check":[40],"conclusion\u2011utility":[43],"check,":[44],"from":[45],"which":[46,55],"usefulness":[48],"decision":[49],"is":[50,93],"derived.":[51],"present":[53],"RULES,":[54],"encodes":[56],"this":[57],"specification":[58],"via":[59],"two\u2011section":[61,144],"trains":[64],"with":[65,95],"reinforcement":[66,148],"learning":[67],"plus":[68],"section\u2011aware":[69,147],"loss":[70],"masking":[71],"to":[72,75],"assign":[73],"penalty":[74],"section":[77],"responsible":[78],"for":[79,152],"errors.":[80],"Training":[81],"evaluation":[83,102],"draw":[84],"diverse":[86],"natural\u2011language":[87],"formal":[89],"proof":[90],"corpora;":[91],"robustness":[92],"assessed":[94],"held\u2011out":[97],"perturbation":[98],"suite;":[99],"end\u2011to\u2011end":[101,138],"spans":[103],"competition\u2011style,":[104],"perturbation\u2011aligned,":[105],"theorem-based":[107],"problems":[108],"across":[109],"various":[110],"LLMs.":[111],"Results":[112],"show":[113],"consistent":[114],"in\u2011domain":[115],"gains":[116,136],"over":[117],"both":[118,150],"vanilla":[120],"single\u2011label":[124],"RL":[125],"baseline,":[126],"larger":[127],"improvements":[128],"applicability\u2011breaking":[130],"perturbations,":[131],"parity":[133],"or":[134],"modest":[135],"tasks;":[139],"ablations":[140],"indicate":[141],"that":[142],"outputs":[145],"are":[149],"necessary":[151],"robustness.":[153]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-16T00:00:00"}