{"id":"https://openalex.org/W7140137854","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.155","title":"TruthTrap: A Bilingual Benchmark for Evaluating Factually Correct Yet Misleading Information in Question Answering","display_name":"TruthTrap: A Bilingual Benchmark for Evaluating Factually Correct Yet Misleading Information in Question Answering","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140137854","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.155"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.155","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.155","pdf_url":"https://aclanthology.org/2026.findings-eacl.155.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: EACL 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.155.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113253015","display_name":"Mohammadamin Shafiei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammadamin Shafiei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099137350","display_name":"Hamidreza Saffari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hamidreza Saffari","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130354994","display_name":"Mohammad Taher Pilehvar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Taher Pilehvar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053806445","display_name":"Alessandro Raganato","orcid":"https://orcid.org/0000-0002-7018-7515"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alessandro Raganato","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.40091724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2966","last_page":"2987"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3357999920845032,"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":0.3357999920845032,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.25850000977516174,"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/T12268","display_name":"Deception detection and forensic psychology","score":0.09359999746084213,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7730000019073486},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5149999856948853},{"id":"https://openalex.org/keywords/information-system","display_name":"Information system","score":0.262800008058548},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2619999945163727}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7730000019073486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.614799976348877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5206999778747559},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5149999856948853},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48249998688697815},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28769999742507935},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24899999797344208},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.24899999797344208}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.155","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.155","pdf_url":"https://aclanthology.org/2026.findings-eacl.155.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: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.155","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.155","pdf_url":"https://aclanthology.org/2026.findings-eacl.155.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: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140137854.pdf","grobid_xml":"https://content.openalex.org/works/W7140137854.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"used":[6],"to":[7,26,109],"answer":[8],"factual,":[9],"informationseeking":[10],"questions":[11],"(ISQs).While":[12],"prior":[13],"work":[14],"often":[15,116],"focuses":[16],"on":[17,55,91],"false":[18],"misleading":[19,97],"information,":[20],"little":[21],"attention":[22],"has":[23],"been":[24],"paid":[25],"true":[27],"but":[28],"strategically":[29],"persuasive":[30],"content":[31],"that":[32,86],"can":[33],"derail":[34],"a":[35,43,61,65,131],"model's":[36],"reasoning.To":[37],"address":[38],"this":[39],"gap,":[40],"we":[41],"introduce":[42],"new":[44],"evaluation":[45],"dataset,":[46],"TRUTH-TRAP,":[47],"in":[48,120,134,151],"two":[49],"languages,":[50],"i.e.,":[51],"English":[52],"and":[53,64,75,81,143,157],"Farsi,":[54],"Iran-related":[56],"ISQs,":[57],"each":[58],"paired":[59],"with":[60],"correct":[62],"explanation":[63],"true-yet-misleading":[66],"hint.We":[67],"then":[68],"evaluate":[69],"nine":[70],"diverse":[71],"LLMs":[72],"(spanning":[73],"proprietary":[74],"open-source":[76],"systems)":[77],"via":[78],"factuality":[79],"classification":[80],"multiple-choice":[82],"QA":[83],"tasks,":[84],"finding":[85],"accuracy":[87],"drops":[88],"by":[89,148],"25%,":[90],"average,":[92],"when":[93],"models":[94,115],"encounter":[95],"these":[96],"yet":[98,122],"factual":[99],"hints.Also,":[100],"the":[101,105,113,138],"models'":[102],"predictions":[103],"match":[104],"hint-aligned":[106],"options":[107],"up":[108],"77":[110],"percent":[111],"of":[112,140],"time.Notably,":[114],"misjudge":[117],"such":[118],"hints":[119],"isolation":[121],"still":[123],"integrate":[124],"them":[125],"into":[126],"final":[127],"answers.Our":[128],"results":[129],"highlight":[130],"significant":[132],"limitation":[133],"LLM":[135],"outputs,":[136],"underscoring":[137],"importance":[139],"robust":[141],"fact-verification":[142],"emphasizing":[144],"real-world":[145],"risks":[146],"posed":[147],"partial":[149],"truths":[150],"domains":[152],"like":[153],"social":[154],"media,":[155],"education,":[156],"policy-making.Our":[158],"dataset":[159],"is":[160],"openly":[161],"available":[162],"at":[163],"https://github.com/Mamin78/":[164],"truthtrap_with_code.":[165]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}