{"id":"https://openalex.org/W4416339534","doi":"https://doi.org/10.18653/v1/2026.acl-long.1951","title":"From Proof to Program: Characterizing Tool-Induced Reasoning Hallucinations in Large Language Models","display_name":"From Proof to Program: Characterizing Tool-Induced Reasoning Hallucinations in Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416339534","doi":"https://doi.org/10.18653/v1/2026.acl-long.1951"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1951","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1951","pdf_url":"https://aclanthology.org/2026.acl-long.1951.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1951.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075330839","display_name":"Farima Fatahi Bayat","orcid":"https://orcid.org/0000-0002-8738-411X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farima Fatahi Bayat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022655234","display_name":"Pouya Pezeshkpour","orcid":"https://orcid.org/0009-0002-7055-0035"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pouya Pezeshkpour","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056213327","display_name":"Estevam Hruschka","orcid":"https://orcid.org/0000-0003-1499-2808"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Estevam Hruschka","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02380572,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"42151","last_page":"42169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.13850000500679016,"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":0.13850000500679016,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.12639999389648438,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.10199999809265137,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5896000266075134},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5163999795913696},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.46650001406669617},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.45739999413490295},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.41609999537467957},{"id":"https://openalex.org/keywords/interpreter","display_name":"Interpreter","score":0.4058000147342682},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.39959999918937683},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.38999998569488525},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.3831000030040741}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6592000126838684},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5896000266075134},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5163999795913696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4823000133037567},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.45739999413490295},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.41609999537467957},{"id":"https://openalex.org/C122783720","wikidata":"https://www.wikidata.org/wiki/Q183065","display_name":"Interpreter","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4018999934196472},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.38999998569488525},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3391999900341034},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.32710000872612},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27970001101493835},{"id":"https://openalex.org/C66153294","wikidata":"https://www.wikidata.org/wiki/Q899291","display_name":"CASP","level":4,"score":0.2768999934196472},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26649999618530273},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1951","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1951","pdf_url":"https://aclanthology.org/2026.acl-long.1951.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.10899","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.10899","pdf_url":"https://arxiv.org/pdf/2511.10899","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.10899","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.10899","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1951","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1951","pdf_url":"https://aclanthology.org/2026.acl-long.1951.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416339534.pdf","grobid_xml":"https://content.openalex.org/works/W4416339534.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tool-augmented":[0],"Language":[1],"Models":[2],"(TaLMs)":[3],"can":[4],"invoke":[5],"external":[6],"tools":[7,35],"to":[8,92,99,110,130,180],"solve":[9],"problems":[10,76],"beyond":[11],"their":[12,100,119],"parametric":[13],"capacity.However,":[14],"it":[15,67],"remains":[16],"unclear":[17],"whether":[18],"these":[19],"tool-enabled":[20],"gains":[21],"reflect":[22],"trustworthy":[23],"reasoning.Focusing":[24],"on":[25],"the":[26,145,152,192],"Code":[27],"Interpreter":[28],"tool,":[29],"we":[30,172],"show":[31],"that":[32,51,105,177],"even":[33],"when":[34],"are":[36],"selected":[37],"and":[38,65,191],"executed":[39],"correctly,":[40],"TaLMs":[41,97,107,179],"treat":[42],"tool":[43,143,158,182,196],"outputs":[44,183],"as":[45,184],"substitutes":[46],"for":[47,77],"reasoning,":[48],"producing":[49],"solutions":[50],"appear":[52],"correct":[53],"but":[54,83],"lack":[55],"coherent":[56,154],"justification.We":[57],"term":[58],"this":[59],"failure":[60],"mode":[61],"Tool-Induced":[62],"Myopia":[63],"(TIM),":[64],"study":[66],"using":[68],"PYMATH,":[69],"a":[70,88,111,148,174],"benchmark":[71],"of":[72,137],"1,679":[73],"competition-level":[74],"mathematical":[75],"which":[78],"Python":[79],"code":[80],"is":[81],"helpful":[82],"not":[84],"sufficient.We":[85],"further":[86],"develop":[87],"multi-dimensional":[89],"evaluation":[90],"suite":[91],"quantify":[93],"reasoning":[94,120,138,156,167,193],"degradation":[95,140],"in":[96,116,134],"relative":[98],"non-tool":[101,125],"counterparts.Our":[102],"findings":[103],"reveal":[104],"while":[106],"achieve":[108],"up":[109,129],"19.3":[112],"percentage":[113],"point":[114],"gain":[115],"final-answer":[117,189],"accuracy,":[118],"behavior":[121],"consistently":[122],"deteriorates":[123],"(e.g.,":[124],"language":[126],"models":[127],"win":[128],"41.5%":[131],"more":[132,146],"often":[133],"pairwise":[135],"comparisons":[136],"processes).This":[139],"intensifies":[141],"with":[142],"use;":[144],"frequently":[147],"model":[149],"invokes":[150],"tools,":[151],"less":[153],"its":[155],"becomes.Moreover,":[157],"use":[159,181],"shifts":[160],"errors":[161],"from":[162],"arithmetic":[163],"mistakes":[164],"toward":[165],"global":[166],"failures":[168],"(logic,":[169],"assumption,":[170],"creativity).Finally,":[171],"propose":[173],"preference-optimization-based":[175],"framework":[176],"realigns":[178],"assistive":[185],"evidence,":[186],"improving":[187],"both":[188],"accuracy":[190],"depth":[194],"under":[195],"use.":[197]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-18T00:00:00"}