{"id":"https://openalex.org/W4414359578","doi":"https://doi.org/10.24963/ijcai.2025/873","title":"Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models","display_name":"Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359578","doi":"https://doi.org/10.24963/ijcai.2025/873"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/873","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047322230","display_name":"Guangzhi Xiong","orcid":"https://orcid.org/0000-0002-8049-5298"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guangzhi Xiong","raw_affiliation_strings":["University of Virginia"],"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039828243","display_name":"Eric Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Xie","raw_affiliation_strings":["University of Virginia"],"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086610701","display_name":"Corey M. Williams","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Corey Williams","raw_affiliation_strings":["University of Virginia"],"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003207510","display_name":"Myles Kim","orcid":"https://orcid.org/0000-0002-0424-5473"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Myles Kim","raw_affiliation_strings":["University of Virginia"],"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114638568","display_name":"Amir Hassan Shariatmadari","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amir Hassan Shariatmadari","raw_affiliation_strings":["University of Virginia"],"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079456168","display_name":"Sikun Guo","orcid":"https://orcid.org/0000-0002-4764-3359"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sikun Guo","raw_affiliation_strings":["University of Virginia"],"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048872833","display_name":"Stefan Bekiranov","orcid":"https://orcid.org/0000-0002-3177-4346"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefan Bekiranov","raw_affiliation_strings":["University of Virginia"],"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101490494","display_name":"Aidong Zhang","orcid":"https://orcid.org/0000-0002-7050-4648"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aidong Zhang","raw_affiliation_strings":["University of Virginia"],"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5047322230"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":8.2359,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.97356359,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7849","last_page":"7857"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8966000080108643,"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":0.8966000080108643,"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":0.8920999765396118,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.8522999882698059,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6085000038146973},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5967000126838684},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5437999963760376},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.4844000041484833},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3790999948978424},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3564000129699707}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6085000038146973},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5967000126838684},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5437999963760376},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5113000273704529},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45170000195503235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4023999869823456},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.38909998536109924},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3564000129699707},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.349700003862381},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31200000643730164},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.29980000853538513},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.295199990272522},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.26010000705718994},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2581999897956848},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C110099512","wikidata":"https://www.wikidata.org/wiki/Q59115","display_name":"Philosophy of science","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/873","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"shown":[5],"significant":[6],"potential":[7],"in":[8,15,35,56,94,112,128,163],"scientific":[9,97,169],"disciplines":[10],"such":[11],"as":[12,42,141],"biomedicine,":[13],"particularly":[14],"hypothesis":[16],"generation,":[17],"where":[18],"they":[19],"can":[20,58],"analyze":[21],"vast":[22],"literature,":[23],"identify":[24],"patterns,":[25],"and":[26,50,99,167,173],"suggest":[27],"research":[28],"directions.":[29],"However,":[30],"a":[31,86,101],"key":[32],"challenge":[33],"lies":[34],"evaluating":[36],"the":[37,53,61,77,90,134,150,159],"truthfulness":[38],"of":[39,63,80,92,153,161],"generated":[40],"hypotheses,":[41,98],"verifying":[43],"their":[44,73],"accuracy":[45],"often":[46],"requires":[47],"substantial":[48],"time":[49],"resources.":[51],"Additionally,":[52],"hallucination":[54,103],"problem":[55],"LLMs":[57,93,119],"lead":[59],"to":[60,105,121],"generation":[62],"hypotheses":[64,109,148,166],"that":[65,118,133],"appear":[66],"plausible":[67],"but":[68],"are":[69,110,176],"ultimately":[70],"incorrect,":[71],"undermining":[72],"reliability.":[74],"To":[75],"facilitate":[76],"systematic":[78],"study":[79],"these":[81],"challenges,":[82],"we":[83,131],"introduce":[84],"TruthHypo,":[85],"benchmark":[87],"for":[88,145],"assessing":[89],"capabilities":[91],"generating":[95],"truthful":[96,123,147,165],"KnowHD,":[100],"knowledge-based":[102],"detector":[104],"evaluate":[106],"how":[107],"well":[108],"grounded":[111],"existing":[113],"knowledge.":[114],"Our":[115,171],"results":[116],"show":[117],"struggle":[120],"generate":[122],"hypotheses.":[124],"By":[125],"analyzing":[126],"hallucinations":[127],"reasoning":[129],"steps,":[130],"demonstrate":[132],"groundedness":[135],"scores":[136],"provided":[137],"by":[138],"KnowHD":[139,162],"serve":[140],"an":[142],"effective":[143],"metric":[144],"filtering":[146],"from":[149],"diverse":[151],"outputs":[152],"LLMs.":[154],"Human":[155],"evaluations":[156],"further":[157],"validate":[158],"utility":[160],"identifying":[164],"accelerating":[168],"discovery.":[170],"data":[172],"source":[174],"code":[175],"available":[177],"at":[178],"https://github.com/Teddy-XiongGZ/TruthHypo.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}