{"id":"https://openalex.org/W4389518898","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.360","title":"INVITE: a Testbed of Automatically Generated Invalid Questions to Evaluate Large Language Models for Hallucinations","display_name":"INVITE: a Testbed of Automatically Generated Invalid Questions to Evaluate Large Language Models for Hallucinations","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389518898","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.360"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.360","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.360","pdf_url":"https://aclanthology.org/2023.findings-emnlp.360.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: EMNLP 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.findings-emnlp.360.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072018684","display_name":"Anil Ramakrishna","orcid":"https://orcid.org/0000-0002-7999-0531"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anil Ramakrishna","raw_affiliation_strings":["Amazon Alexa AI"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075937808","display_name":"Rahul Gupta","orcid":"https://orcid.org/0000-0002-9277-3718"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Gupta","raw_affiliation_strings":["Amazon Alexa AI"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067133778","display_name":"Jens Lehmann","orcid":"https://orcid.org/0000-0001-9108-4278"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jens Lehmann","raw_affiliation_strings":["Amazon Alexa AI"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058753263","display_name":"Morteza Ziyadi","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Morteza Ziyadi","raw_affiliation_strings":["Amazon Alexa AI"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072018684"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.5245,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72710587,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5422","last_page":"5429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9976999759674072,"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/T13629","display_name":"Text Readability and Simplification","score":0.9919999837875366,"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/testbed","display_name":"Testbed","score":0.6466598510742188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6413177251815796},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6357241272926331},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5946754217147827},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.5858785510063171},{"id":"https://openalex.org/keywords/hallucinating","display_name":"Hallucinating","score":0.5688848495483398},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.4084465801715851},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35994553565979004},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3468629717826843},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.32939910888671875},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14824959635734558},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10904636979103088}],"concepts":[{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.6466598510742188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6413177251815796},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6357241272926331},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5946754217147827},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.5858785510063171},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.5688848495483398},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4084465801715851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35994553565979004},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3468629717826843},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32939910888671875},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14824959635734558},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10904636979103088},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.findings-emnlp.360","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.360","pdf_url":"https://aclanthology.org/2023.findings-emnlp.360.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: EMNLP 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.360","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.360","pdf_url":"https://aclanthology.org/2023.findings-emnlp.360.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: EMNLP 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389518898.pdf","grobid_xml":"https://content.openalex.org/works/W4389518898.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1552847225","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2757978590","https://openalex.org/W2936695845","https://openalex.org/W2963323070","https://openalex.org/W2963339397","https://openalex.org/W2963748441","https://openalex.org/W2963969878","https://openalex.org/W3118781290","https://openalex.org/W3173465197","https://openalex.org/W3212496002","https://openalex.org/W4221159672","https://openalex.org/W4226278401","https://openalex.org/W4286750487","https://openalex.org/W4288102879","https://openalex.org/W4307123345","https://openalex.org/W4309674289","https://openalex.org/W4320854935","https://openalex.org/W4322718191","https://openalex.org/W4353015365","https://openalex.org/W4385468994","https://openalex.org/W4385572448","https://openalex.org/W4386566565","https://openalex.org/W4388488349"],"related_works":["https://openalex.org/W3204676188","https://openalex.org/W2992803471","https://openalex.org/W2066036438","https://openalex.org/W2078454190","https://openalex.org/W2963350370","https://openalex.org/W2930227984","https://openalex.org/W2108123836","https://openalex.org/W2063248114","https://openalex.org/W2883256816","https://openalex.org/W2528648655"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,163,194],"Large":[3],"language":[4,140],"models":[5,141],"(LLMs)":[6],"have":[7],"enabled":[8],"them":[9,57],"to":[10,23,49,55,86,93,110,115,137,151,191],"hold":[11],"free":[12],"form":[13],"conversations":[14],"over":[15],"multiple":[16],"turns,":[17],"but":[18],"they":[19],"exhibit":[20],"a":[21,130,153,181],"tendency":[22],"make":[24],"unfounded":[25],"and":[26,114,187],"incorrect":[27,44],"statements,":[28],"commonly":[29],"known":[30],"as":[31,65],"hallucinations.In":[32,143],"particular,":[33],"LLMs":[34,51,67,121,179],"hallucinate":[35],"frequently":[36],"when":[37],"given":[38],"invalid":[39,124,157],"questions,":[40],"i.e.":[41],"ones":[42],"with":[43],"assumptions.The":[45],"most":[46],"common":[47],"approach":[48],"evaluate":[50,173],"on":[52,58,71,99],"hallucinations":[53,193],"is":[54,148],"test":[56,62,84,101],"Question":[59],"Answering":[60],"(QA)":[61],"sets":[63,85],"such":[64],"TruthfulQA.However,":[66],"are":[68,168],"increasingly":[69],"pretrained":[70],"massive":[72],"text":[73],"corpora":[74],"scraped":[75],"from":[76],"the":[77,87,177],"Internet,":[78],"which":[79,164],"may":[80],"inevitably":[81],"expose":[82],"these":[83,100,195],"model":[88,97],"during":[89],"training,":[90],"leading":[91],"eventually":[92],"an":[94,107],"overestimation":[95],"of":[96,132,156,176],"performances":[98],"sets.In":[102],"this":[103,112],"work,":[104],"we":[105],"present":[106],"alternative":[108],"framework":[109,128,147,186],"address":[111],"risk":[113],"foster":[116],"further":[117],"research":[118],"towards":[119],"making":[120],"robust":[122],"against":[123,180],"questions.We":[125],"name":[126],"our":[127,146,185],"INVITE:":[129],"testbed":[131],"automatically":[133],"generated":[134,183],"INValId":[135],"questions":[136,158],"evaluaTE":[138],"large":[139],"for":[142],"each":[144],"instantiation,":[145],"set":[149],"up":[150],"create":[152],"fresh":[154],"batch":[155],"by":[159,170,184],"distorting":[160],"valid":[161],"facts":[162],"subjects":[165],"or":[166],"objects":[167],"replaced":[169],"similar":[171],"entities.We":[172],"several":[174],"state":[175],"art":[178],"testset":[182],"highlight":[188],"its":[189],"capacity":[190],"trigger":[192],"models.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-01-22T23:29:09.771500","created_date":"2025-10-10T00:00:00"}