{"id":"https://openalex.org/W7138391786","doi":"https://doi.org/10.1609/aaai.v40i38.40495","title":"From Detection to Diagnosis: Advancing Hallucination Analysis with Automated Data Synthesis","display_name":"From Detection to Diagnosis: Advancing Hallucination Analysis with Automated Data Synthesis","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138391786","doi":"https://doi.org/10.1609/aaai.v40i38.40495"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i38.40495","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40495","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i38.40495","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129684855","display_name":"Yanyi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanyi Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129746796","display_name":"Qingwen Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingwen Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101285251","display_name":"Tiezheng Guo","orcid":"https://orcid.org/0009-0009-2240-6830"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tiezheng Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129699506","display_name":"Feiyu Qu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feiyu Qu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129642314","display_name":"Jun Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5116410700","display_name":"Yingyou Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingyou Wen","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":0.24001996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"38","first_page":"32222","last_page":"32230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.2678000032901764,"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":0.2678000032901764,"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/T10028","display_name":"Topic Modeling","score":0.05939999967813492,"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":0.052299998700618744,"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/task","display_name":"Task (project management)","score":0.5699999928474426},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5655999779701233},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5439000129699707},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4348999857902527},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4339999854564667},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.43140000104904175},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4203000068664551},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.3783999979496002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505000233650208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6190999746322632},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5699999928474426},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5655999779701233},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5439000129699707},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5242000222206116},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43140000104904175},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39329999685287476},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30489999055862427},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2773999869823456},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26249998807907104},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1609/aaai.v40i38.40495","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40495","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2601.09734","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.09734","pdf_url":"https://arxiv.org/pdf/2601.09734","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ojs.aaai.org:article/40495","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/40495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i38.40495","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40495","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.42061734199523926}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Hallucinations":[0],"in":[1,25],"Large":[2],"Language":[3],"Models":[4],"(LLMs),":[5],"defined":[6],"as":[7],"the":[8,99,172,189,203],"generation":[9],"of":[10,39,191,207],"content":[11,95],"inconsistent":[12],"with":[13,113,149],"facts":[14],"or":[15],"context,":[16],"represent":[17],"a":[18,60,77,138,150,197],"core":[19],"obstacle":[20],"to":[21,43,69,82,179],"their":[22],"reliable":[23,219],"deployment":[24],"critical":[26],"domains.":[27],"Current":[28],"research":[29,62],"primarily":[30],"focuses":[31],"on":[32,171],"binary":[33],"\"detection\"":[34,68],"approaches":[35],"that,":[36],"while":[37,175,195],"capable":[38],"identifying":[40],"hallucinations,":[41,86],"fail":[42],"provide":[44],"interpretable":[45],"and":[46,94,128,157,205,218],"actionable":[47],"feedback":[48],"for":[49,214],"model":[50,165],"improvement,":[51],"thus":[52],"limiting":[53],"practical":[54],"utility.":[55],"To":[56],"address":[57],"this":[58],"limitation,":[59],"new":[61],"paradigm":[63],"is":[64,75],"proposed,":[65],"shifting":[66],"from":[67,117],"\"diagnosis\".":[70],"The":[71],"Hallucination":[72,100],"Diagnosis":[73,101],"Task":[74],"introduced,":[76],"task":[78],"which":[79],"requires":[80],"models":[81,170,194],"not":[83],"only":[84],"detect":[85],"but":[87],"also":[88],"perform":[89],"error":[90],"localization,":[91],"causal":[92],"explanation,":[93],"correction.":[96],"We":[97],"develop":[98],"Generator":[102],"(HDG),":[103],"an":[104,211],"automated":[105],"pipeline":[106],"that":[107,163],"systematically":[108],"generates":[109],"high-quality":[110],"training":[111],"samples":[112],"rich":[114],"diagnostic":[115],"metadata":[116],"raw":[118],"corpora":[119],"through":[120],"multi-dimensional":[121],"augmentation":[122],"strategies":[123],"including":[124],"controlled":[125],"fact":[126],"fabrication":[127],"reasoning":[129],"chain":[130],"perturbation.":[131],"Using":[132],"HDG-generated":[133],"data,":[134],"we":[135],"train":[136],"HDM-4B-RL,":[137],"4-billion-parameter":[139],"hallucination":[140,208],"diagnosis":[141,185],"model,":[142],"employing":[143],"Group":[144],"Relative":[145],"Policy":[146],"Optimization":[147],"(GRPO)":[148],"comprehensive":[151,184],"reward":[152],"function":[153],"incorporating":[154],"structural,":[155],"accuracy,":[156],"localization":[158],"signals.":[159],"Experimental":[160],"results":[161],"demonstrate":[162],"our":[164],"surpasses":[166],"previous":[167],"state-of-the-art":[168],"detection":[169],"HaluEval":[173],"benchmark":[174],"achieving":[176],"comparable":[177],"performance":[178],"advanced":[180],"general-purpose":[181],"models.":[182],"In":[183],"tasks,":[186],"HDM-4B-RL":[187],"matches":[188],"capabilities":[190],"larger":[192],"general":[193],"maintaining":[196],"smaller":[198],"size.":[199],"This":[200],"work":[201],"validates":[202],"feasibility":[204],"value":[206],"diagnosis,":[209],"providing":[210],"effective":[212],"methodology":[213],"building":[215],"more":[216],"trustworthy":[217],"generative":[220],"AI":[221],"systems.":[222]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}