{"id":"https://openalex.org/W4414462928","doi":"https://doi.org/10.1109/access.2025.3613851","title":"Evaluating the Effectiveness of Advanced Language Models in Detecting and Mitigating Hallucinations Using Structured Question- Answering, Novel Metrics, and Post-Hoc Retrieval","display_name":"Evaluating the Effectiveness of Advanced Language Models in Detecting and Mitigating Hallucinations Using Structured Question- Answering, Novel Metrics, and Post-Hoc Retrieval","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414462928","doi":"https://doi.org/10.1109/access.2025.3613851"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3613851","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3613851","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3613851","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115489869","display_name":"Rana Hassan Ajmal","orcid":null},"institutions":[{"id":"https://openalex.org/I194348271","display_name":"Government College University, Faisalabad","ror":"https://ror.org/051zgra59","country_code":"PK","type":"education","lineage":["https://openalex.org/I194348271"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Rana Hassan Ajmal","raw_affiliation_strings":["Department of Computer Science, Government College University, Faisalabad, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Government College University, Faisalabad, Pakistan","institution_ids":["https://openalex.org/I194348271"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047173698","display_name":"Muhammad Umer Sarwar","orcid":"https://orcid.org/0000-0001-6790-1979"},"institutions":[{"id":"https://openalex.org/I194348271","display_name":"Government College University, Faisalabad","ror":"https://ror.org/051zgra59","country_code":"PK","type":"education","lineage":["https://openalex.org/I194348271"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Umer Sarwar","raw_affiliation_strings":["Department of Computer Science, Government College University, Faisalabad, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Government College University, Faisalabad, Pakistan","institution_ids":["https://openalex.org/I194348271"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082204963","display_name":"Muhammad Kashif Hanif","orcid":"https://orcid.org/0000-0001-5150-2228"},"institutions":[{"id":"https://openalex.org/I194348271","display_name":"Government College University, Faisalabad","ror":"https://ror.org/051zgra59","country_code":"PK","type":"education","lineage":["https://openalex.org/I194348271"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Kashif Hanif","raw_affiliation_strings":["Department of Computer Science, Government College University, Faisalabad, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Government College University, Faisalabad, Pakistan","institution_ids":["https://openalex.org/I194348271"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072217554","display_name":"Muhammad Irfan Khan","orcid":"https://orcid.org/0000-0003-1128-7337"},"institutions":[{"id":"https://openalex.org/I194348271","display_name":"Government College University, Faisalabad","ror":"https://ror.org/051zgra59","country_code":"PK","type":"education","lineage":["https://openalex.org/I194348271"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Irfan Khan","raw_affiliation_strings":["Department of Computer Science, Government College University, Faisalabad, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Government College University, Faisalabad, Pakistan","institution_ids":["https://openalex.org/I194348271"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5115489869"],"corresponding_institution_ids":["https://openalex.org/I194348271"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":4.7589,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95087139,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"13","issue":null,"first_page":"173805","last_page":"173812"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.9954000115394592,"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"}},"topics":[{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.9954000115394592,"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"}},{"id":"https://openalex.org/T10272","display_name":"Mental Health Treatment and Access","score":0.9848999977111816,"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"}},{"id":"https://openalex.org/T13283","display_name":"Mental Health Research Topics","score":0.9605000019073486,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/hallucinating","display_name":"Hallucinating","score":0.9000999927520752},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5139999985694885},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.486299991607666},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46939998865127563},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4681999981403351},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42179998755455017},{"id":"https://openalex.org/keywords/misinformation","display_name":"Misinformation","score":0.414000004529953},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.3287000060081482}],"concepts":[{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.9000999927520752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876999974250793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5519999861717224},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5139999985694885},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.486299991607666},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4681999981403351},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4438999891281128},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41850000619888306},{"id":"https://openalex.org/C2776990098","wikidata":"https://www.wikidata.org/wiki/Q13579947","display_name":"Misinformation","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C2780505938","wikidata":"https://www.wikidata.org/wiki/Q17093282","display_name":"Unavailability","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27720001339912415},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C2776412080","wikidata":"https://www.wikidata.org/wiki/Q7431605","display_name":"Schizophrenia (object-oriented programming)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3613851","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3613851","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2d3b711f223b420bb38a24f746c6697e","is_oa":true,"landing_page_url":"https://doaj.org/article/2d3b711f223b420bb38a24f746c6697e","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 173805-173812 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3613851","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3613851","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W3034383590","https://openalex.org/W3155584966","https://openalex.org/W4389520749","https://openalex.org/W4393160204","https://openalex.org/W4401990406","https://openalex.org/W4402670231","https://openalex.org/W4402670429","https://openalex.org/W4402671735","https://openalex.org/W4402871942","https://openalex.org/W4404534210","https://openalex.org/W4404781595","https://openalex.org/W4404781825","https://openalex.org/W4408347326","https://openalex.org/W4408352939","https://openalex.org/W4409362692"],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,46,81,158,171,180,196,202],"rapidly":[2],"evolving":[3],"field":[4],"of":[5,49,97,173,182,195,204],"Artificial":[6],"Intelligence":[7],"(AI),":[8],"Large":[9],"Language":[10,20],"Models":[11],"(LLMs)":[12],"have":[13],"demonstrated":[14,102],"significant":[15],"potential":[16],"across":[17,132],"various":[18],"Natural":[19],"Processing":[21],"(NLP)":[22],"applications.":[23,219],"However,":[24],"a":[25,54,59,91],"persistent":[26],"challenge":[27],"remains":[28],"in":[29,51,118,189,217],"their":[30],"tendency":[31],"to":[32,75,178,210],"hallucinate,":[33],"producing":[34],"content":[35],"that":[36,103,123,170],"appears":[37],"credible":[38],"but":[39],"is":[40],"factually":[41],"inaccurate.":[42],"This":[43,199],"paper":[44],"addresses":[45],"critical":[47],"issues":[48],"hallucinations":[50],"LLMs":[52],"through":[53,107],"multi-dimensional":[55],"approach.":[56],"We":[57],"developed":[58],"high-quality":[60],"question":[61],"answering":[62],"(QA)":[63],"dataset":[64],"spanning":[65],"15":[66],"academic":[67],"disciplines,":[68],"comprising":[69],"500":[70],"questions":[71],"with":[72],"controlled":[73],"hallucination":[74],"facilitate":[76],"systematic":[77],"analysis.":[78],"To":[79],"evaluate":[80],"correspondence":[82],"between":[83],"generated":[84],"responses":[85,181],"and":[86,129,140,164,192,214],"source":[87],"data,":[88,156],"we":[89,101],"introduce":[90],"novel":[92],"metric,":[93],"enabling":[94],"effective":[95],"detection":[96],"hallucinated":[98,155,197],"content.":[99],"Finally,":[100],"incorporating":[104],"external":[105],"information":[106],"post-hoc":[108,174],"retrieval":[109,175],"procedures":[110],"significantly":[111],"reduces":[112],"hallucination,":[113],"which":[114],"improves":[115],"factual":[116],"accuracy":[117],"responses.":[119],"Our":[120,166],"findings":[121],"indicate":[122],"GPT-4":[124,127,150],"consistently":[125],"outperforms":[126],"Turbo":[128,131],"GPT-3.5":[130],"multiple":[133],"performance":[134],"metrics,":[135],"including":[136],"accuracy,":[137],"precision,":[138,190],"recall,":[139,191],"F1":[141,193],"score.":[142],"Despite":[143],"its":[144],"effectiveness":[145],"at":[146],"minimizing":[147],"false":[148],"positives,":[149],"exhibits":[151],"moderated":[152],"recall":[153],"for":[154,160],"suggesting":[157],"need":[159],"continuous":[161],"model":[162],"evaluation":[163],"optimization.":[165],"improved":[167],"analysis":[168],"proves":[169],"use":[172],"helps":[176],"considerably":[177],"make":[179],"LLM":[183],"more":[184],"factual,":[185],"displaying":[186],"large":[187],"improvement":[188],"score":[194],"data.":[198],"study":[200],"enhances":[201],"reliability":[203],"question-answering":[205],"systems,":[206],"providing":[207],"scalable":[208],"methods":[209],"mitigate":[211],"misinformation":[212],"risk":[213],"improve":[215],"trustworthiness":[216],"real-world":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
