{"id":"https://openalex.org/W7166826360","doi":"https://doi.org/10.18653/v1/2026.acl-long.1112","title":"Truth or Sophistry? LoFa: A Benchmark for LLM Robustness Against Logical Fallacies","display_name":"Truth or Sophistry? LoFa: A Benchmark for LLM Robustness Against Logical Fallacies","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166826360","doi":"https://doi.org/10.18653/v1/2026.acl-long.1112"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1112","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1112","pdf_url":"https://aclanthology.org/2026.acl-long.1112.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":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1112.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139852011","display_name":"Xudong Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xudong Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139798039","display_name":"li Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"li Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139848980","display_name":"Ye Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139847356","display_name":"Xin Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139763987","display_name":"Yi Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139720483","display_name":"Zhiyong Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","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":0.81599106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24236","last_page":"24268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.6608999967575073,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.6608999967575073,"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":0.0333000011742115,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.031199999153614044,"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/robustness","display_name":"Robustness (evolution)","score":0.7009999752044678},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4668999910354614},{"id":"https://openalex.org/keywords/truth-table","display_name":"Truth table","score":0.31209999322891235},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.23669999837875366}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7009999752044678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5961999893188477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48579999804496765},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4668999910354614},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3513999879360199},{"id":"https://openalex.org/C56949724","wikidata":"https://www.wikidata.org/wiki/Q219079","display_name":"Truth table","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2872999906539917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2847000062465668},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.23669999837875366},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.23270000517368317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1112","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1112","pdf_url":"https://aclanthology.org/2026.acl-long.1112.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1112","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1112","pdf_url":"https://aclanthology.org/2026.acl-long.1112.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":[{"id":"https://openalex.org/G2603945996","display_name":null,"funder_award_id":"62076144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5546164793","display_name":null,"funder_award_id":"JCYJ20220818101014030","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166826360.pdf","grobid_xml":"https://content.openalex.org/works/W7166826360.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"exhibit":[5,118],"strong":[6],"semantic":[7],"capabilities,":[8],"their":[9,36],"resilience":[10,88],"to":[11,30,58,85,92,110,121],"manipulative":[12],"linguistic":[13],"patterns":[14],"like":[15],"logical":[16],"fallacies":[17,40],"remains":[18,44],"an":[19],"underexplored":[20],"area.Prior":[21],"work":[22],"has":[23],"focused":[24],"on":[25],"the":[26,66],"ability":[27],"of":[28,124],"LLMs":[29,117],"identify":[31],"or":[32],"classify":[33],"fallacies,":[34,125],"but":[35],"robustness":[37,61,94,120],"against":[38,62],"these":[39],"in":[41],"persuasive":[42],"contexts":[43],"largely":[45],"unexplored.To":[46],"address":[47],"this":[48],"gap,":[49],"we":[50,79,101],"introduce":[51],"LoFa":[52,67],"(Logical":[53,107],"Fallacy),":[54],"a":[55,70,81,96,103],"comprehensive":[56],"benchmark":[57],"evaluate":[59],"LLM":[60],"fallacies.We":[63],"first":[64],"construct":[65],"dataset":[68],"via":[69],"multi-agent":[71],"pipeline,":[72],"pairing":[73],"factual":[74],"questions":[75],"with":[76],"fallacious":[77],"arguments.Then,":[78],"develop":[80],"multi-round":[82],"debate":[83],"framework":[84],"assess":[86],"model":[87],"under":[89],"sustained":[90],"attacks.Furthermore,":[91],"disentangle":[93],"from":[95],"model's":[97],"inherent":[98],"knowledge":[99],"limitations,":[100],"propose":[102],"new":[104],"metric,":[105],"LFR@k":[106],"Fallacy":[108],"Resistance),":[109],"quantify":[111],"performance.Our":[112],"experiments":[113],"reveal":[114],"that":[115],"different":[116],"varied":[119],"distinct":[122],"types":[123],"highlighting":[126],"unique":[127],"vulnerability":[128],"profiles":[129],"across":[130],"models.":[131]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}