{"id":"https://openalex.org/W4416235607","doi":"https://doi.org/10.18653/v1/2026.findings-acl.65","title":"EVADE: LLM-Based Explanation Generation and Validation for Error Detection in NLI","display_name":"EVADE: LLM-Based Explanation Generation and Validation for Error Detection in NLI","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416235607","doi":"https://doi.org/10.18653/v1/2026.findings-acl.65"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.65","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.65","pdf_url":"https://aclanthology.org/2026.findings-acl.65.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: ACL 2026","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.findings-acl.65.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111271041","display_name":"Longfei Zuo","orcid":null},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I41121874","display_name":"Heilbronn University","ror":"https://ror.org/04g5gcg95","country_code":"DE","type":"education","lineage":["https://openalex.org/I41121874"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Longfei Zuo","raw_affiliation_strings":["MaiNLP , Center for Information and Language Processing , LMU Munich , Germany","Technical University of Munich , Heilbronn , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MaiNLP , Center for Information and Language Processing , LMU Munich , Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"raw_affiliation_string":"Technical University of Munich , Heilbronn , Germany","institution_ids":["https://openalex.org/I41121874","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088832285","display_name":"Barbara Plank","orcid":"https://orcid.org/0000-0002-4394-1965"},"institutions":[{"id":"https://openalex.org/I292141241","display_name":"Munich School of Philosophy","ror":"https://ror.org/02kqy4228","country_code":"DE","type":"education","lineage":["https://openalex.org/I292141241"]},{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Barbara Plank","raw_affiliation_strings":["MaiNLP , Center for Information and Language Processing , LMU Munich , Germany","Munich Center for Machine Learning (MCML) , Munich , Germany LMU Munich "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MaiNLP , Center for Information and Language Processing , LMU Munich , Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"raw_affiliation_string":"Munich Center for Machine Learning (MCML) , Munich , Germany LMU Munich ","institution_ids":["https://openalex.org/I292141241","https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008224824","display_name":"Siyao Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I292141241","display_name":"Munich School of Philosophy","ror":"https://ror.org/02kqy4228","country_code":"DE","type":"education","lineage":["https://openalex.org/I292141241"]},{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Siyao Peng","raw_affiliation_strings":["MaiNLP , Center for Information and Language Processing , LMU Munich , Germany","Munich Center for Machine Learning (MCML) , Munich , Germany LMU Munich "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MaiNLP , Center for Information and Language Processing , LMU Munich , Germany","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"raw_affiliation_string":"Munich Center for Machine Learning (MCML) , Munich , Germany LMU Munich ","institution_ids":["https://openalex.org/I292141241","https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.02286518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1286","last_page":"1300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.5609999895095825,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.5609999895095825,"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":0.14980000257492065,"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":0.03840000182390213,"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/annotation","display_name":"Annotation","score":0.5823000073432922},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5142999887466431},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4796000123023987},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.47870001196861267},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.39579999446868896},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3716999888420105},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.34769999980926514},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.32089999318122864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731999754905701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5867999792098999},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5823000073432922},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5142999887466431},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4796000123023987},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.47870001196861267},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43639999628067017},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3785000145435333},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.30309998989105225},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2883000075817108},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C169806903","wikidata":"https://www.wikidata.org/wiki/Q5937752","display_name":"Human error","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.65","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.65","pdf_url":"https://aclanthology.org/2026.findings-acl.65.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: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.08949","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.08949","pdf_url":"https://arxiv.org/pdf/2511.08949","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.08949","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.08949","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.65","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.65","pdf_url":"https://aclanthology.org/2026.findings-acl.65.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320336290","display_name":"Institute for Advanced Study, Technische Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05fj6by70"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416235607.pdf","grobid_xml":"https://content.openalex.org/works/W4416235607.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"High-quality":[0],"datasets":[1],"are":[2,25],"critical":[3],"for":[4,27,94,115],"training":[5,149],"and":[6,60,78,96,122,143],"evaluating":[7],"reliable":[8],"NLP":[9],"models.In":[10],"tasks":[11],"like":[12],"natural":[13],"language":[14,104],"inference":[15],"(NLI),":[16],"human":[17,141,161,171],"label":[18,54,178],"variation":[19],"(HLV)":[20],"arises":[21],"when":[22],"multiple":[23,49],"labels":[24,85],"valid":[26],"the":[28,57,67,81,164],"same":[29],"instance,":[30],"making":[31],"it":[32],"difficult":[33],"to":[34,51,99,136,166],"separate":[35],"annotation":[36,75],"errors":[37,62,101,114,147,158],"from":[38,148],"plausible":[39,84],"variation.An":[40],"earlier":[41],"framework,":[42,92],"VARI-ERR":[43],"(Weber-Genzel":[44],"et":[45],"al.,":[46],"2024),":[47],"asks":[48],"annotators":[50],"explain":[52],"their":[53],"decisions":[55],"in":[56,66,153],"first":[58],"round":[59],"flags":[61],"through":[63],"validity":[64],"judgments":[65],"second":[68],"round.However,":[69],"conducting":[70],"two":[71],"rounds":[72],"of":[73,83],"manual":[74],"is":[76],"costly":[77],"may":[79],"limit":[80],"coverage":[82],"or":[86],"explanations.Our":[87],"study":[88],"proposes":[89],"a":[90,108],"new":[91],"EVADE,":[93],"generating":[95],"validating":[97],"explanations":[98],"detect":[100],"using":[102],"large":[103],"models":[105],"(LLMs).We":[106],"perform":[107],"comprehensive":[109],"analysis":[110],"comparing":[111],"human-and":[112],"LLM-detected":[113,146],"NLI":[116],"across":[117],"distribution":[118],"comparison,":[119],"validation":[120,131],"overlap,":[121],"impact":[123],"on":[124],"model":[125],"fine-tuning.Our":[126],"experiments":[127],"demonstrate":[128],"that":[129,144],"LLM":[130],"refines":[132],"generated":[133],"explanation":[134],"distributions":[135],"more":[137],"closely":[138],"align":[139],"with":[140],"annotations,":[142],"removing":[145,157],"data":[150],"yields":[151],"improvements":[152],"fine-tuning":[154],"performance":[155],"than":[156],"identified":[159],"by":[160],"annotators.This":[162],"highlights":[163],"potential":[165],"scale":[167],"error":[168],"detection,":[169],"reducing":[170],"effort":[172],"while":[173],"improving":[174],"dataset":[175],"quality":[176],"under":[177],"variation.":[179]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-11-14T00:00:00"}