{"id":"https://openalex.org/W7208513455","doi":null,"title":"TRUTHFULNESS UNDER PROMPTS: SYSTEMATIC EVALUATION OF HALLUCINATIONS IN LLMS WITH TRUTHFULQA","display_name":"TRUTHFULNESS UNDER PROMPTS: SYSTEMATIC EVALUATION OF HALLUCINATIONS IN LLMS WITH TRUTHFULQA","publication_year":2025,"publication_date":"2025-09-20","ids":{"openalex":"https://openalex.org/W7208513455"},"language":"en","primary_location":{"id":"pmh:oai:irdb.nii.ac.jp:00835:0007271839","doi":null,"is_oa":true,"landing_page_url":"https://waseda.repo.nii.ac.jp/records/2007429","pdf_url":"https://waseda.repo.nii.ac.jp/record/2007429/files/t5123fg28.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"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":"master thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://waseda.repo.nii.ac.jp/record/2007429/files/t5123fg28.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5149624352","display_name":"Xuyi Zheng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zheng, Xuyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5149624352"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8432999849319458,"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":0.8432999849319458,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.07559999823570251,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.03229999914765358,"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/hallucinations","display_name":"hallucinations","score":0.6320000290870667},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9399999976158142},{"id":"https://openalex.org/keywords/prompting-strategies","display_name":"prompting strategies","score":0.9629999995231628},{"id":"https://openalex.org/keywords/adversarial-prompting","display_name":"adversarial prompting","score":0.4490000009536743},{"id":"https://openalex.org/keywords/multiple-choice-question-answering","display_name":"multiple-choice question answering","score":0.6629999876022339},{"id":"https://openalex.org/keywords/factual-reliability","display_name":"factual reliability","score":0.37299999594688416},{"id":"https://openalex.org/keywords/model-credibility","display_name":"model credibility","score":0.6340000033378601}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6772000193595886},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.640500009059906},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5767999887466431},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.517799973487854},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5092999935150146},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4916999936103821},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4449999928474426},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4309000074863434},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.4138000011444092},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33970001339912415},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2854999899864197},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2558000087738037},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:irdb.nii.ac.jp:00835:0007271839","doi":null,"is_oa":true,"landing_page_url":"https://waseda.repo.nii.ac.jp/records/2007429","pdf_url":"https://waseda.repo.nii.ac.jp/record/2007429/files/t5123fg28.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"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":"master thesis"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:00835:0007271839","doi":null,"is_oa":true,"landing_page_url":"https://waseda.repo.nii.ac.jp/records/2007429","pdf_url":"https://waseda.repo.nii.ac.jp/record/2007429/files/t5123fg28.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"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":"master thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7208513455.pdf","grobid_xml":"https://content.openalex.org/works/W7208513455.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W4362515116","https://openalex.org/W4385262268","https://openalex.org/W4387432111","https://openalex.org/W7120088840"],"related_works":["https://openalex.org/W4402683996","https://openalex.org/W7084062577","https://openalex.org/W4400305024","https://openalex.org/W7151512747","https://openalex.org/W4393146683","https://openalex.org/W4412404236","https://openalex.org/W4402670137","https://openalex.org/W4409671508","https://openalex.org/W7053377175","https://openalex.org/W4412945709"],"abstract_inverted_index":{"Large":[0],"language":[1,157],"models":[2],"(LLMs)":[3],"have":[4],"achieved":[5],"remarkable":[6],"progress":[7],"in":[8,24,39,105],"Natural":[9],"Language":[10],"Processing":[11],"(NLP),":[12],"significantly":[13],"enhancing":[14],"the":[15,48,55,61,80,95,98,106,111,135,139,150],"performance":[16],"of":[17,50,57,82,113,122,142,152],"core":[18],"NLP":[19],"tasks":[20,102],"and":[21,100,155],"enabling":[22],"breakthroughs":[23],"various":[25],"application":[26],"domains.However,":[27],"recent":[28],"LLMs":[29,84],"remain":[30],"prone":[31],"to":[32,68,72,85,97],"generating":[33],"hallucinations-statements":[34],"that":[35,126],"are":[36],"not":[37],"grounded":[38],"real-world":[40],"facts":[41],"or":[42,115,132],"input":[43],"data-which":[44],"poses":[45],"challenges":[46],"for":[47,149],"reliability":[49],"model":[51],"outputs.To":[52],"systematically":[53],"assess":[54],"truthfulness":[56,141],"LLMs,":[58],"we":[59,77,93],"leverage":[60],"TruthfulQA":[62,107],"benchmark,":[63,108],"which":[64,109],"is":[65],"adversarially":[66],"designed":[67],"test":[69],"models'":[70],"susceptibility":[71],"imitative":[73],"falsehoods.In":[74],"this":[75],"study,":[76],"comprehensively":[78],"analyze":[79],"ability":[81],"state-of-the-art":[83],"produce":[86],"truthful":[87],"responses":[88],"under":[89],"different":[90],"prompting":[91,129],"strategies.Additionally,":[92],"extend":[94],"evaluation":[96],"MC1":[99],"MC2":[101],"officially":[103],"specified":[104],"require":[110],"identification":[112],"single":[114],"multiple":[116],"correct":[117],"answers":[118],"from":[119],"a":[120,127],"set":[121],"options.Our":[123],"results":[124],"demonstrate":[125],"novel":[128],"approach-by":[130],"encouraging":[131],"even":[133],"misleading":[134],"model-can":[136],"substantially":[137],"improve":[138],"average":[140],"LLM-generated":[143],"responses.These":[144],"findings":[145],"offer":[146],"valuable":[147],"insights":[148],"development":[151],"more":[153],"reliable":[154],"trustworthy":[156],"models.":[158]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-04T00:00:00"}