{"id":"https://openalex.org/W4403577490","doi":"https://doi.org/10.1145/3627673.3679222","title":"AuditLLM: A Tool for Auditing Large Language Models Using Multiprobe Approach","display_name":"AuditLLM: A Tool for Auditing Large Language Models Using Multiprobe Approach","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403577490","doi":"https://doi.org/10.1145/3627673.3679222"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679222","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679222","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3627673.3679222","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023630015","display_name":"Maryam Amirizaniani","orcid":"https://orcid.org/0000-0002-6142-0637"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maryam Amirizaniani","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6142-0637","affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113247992","display_name":"Elias Martin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138624","display_name":"University of Washington Bothell","ror":"https://ror.org/02ygzhr13","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210138624"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elias Martin","raw_affiliation_strings":["University of Washington - Bothell, Bothell, WA, USA"],"raw_orcid":"https://orcid.org/0009-0008-3178-1408","affiliations":[{"raw_affiliation_string":"University of Washington - Bothell, Bothell, WA, USA","institution_ids":["https://openalex.org/I4210138624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038162360","display_name":"Tanya Roosta","orcid":"https://orcid.org/0009-0003-1235-3006"},"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"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanya Roosta","raw_affiliation_strings":["UC Berkeley & Amazon, Palo Alto, CA, USA"],"raw_orcid":"https://orcid.org/0009-0003-1235-3006","affiliations":[{"raw_affiliation_string":"UC Berkeley & Amazon, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047032131","display_name":"Aman Chadha","orcid":"https://orcid.org/0000-0001-6621-9003"},"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"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aman Chadha","raw_affiliation_strings":["Stanford University &, Amazon GenAI, Palo Alto, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6621-9003","affiliations":[{"raw_affiliation_string":"Stanford University &, Amazon GenAI, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061319881","display_name":"Chirag Shah","orcid":"https://orcid.org/0000-0002-3797-4293"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chirag Shah","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3797-4293","affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5174","last_page":"5179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.9984999895095825,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9721999764442444,"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/computer-science","display_name":"Computer science","score":0.7204875349998474},{"id":"https://openalex.org/keywords/audit","display_name":"Audit","score":0.6373883485794067},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.39854153990745544},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.340914249420166},{"id":"https://openalex.org/keywords/accounting","display_name":"Accounting","score":0.12403765320777893},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.08329427242279053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7204875349998474},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.6373883485794067},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.39854153990745544},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.340914249420166},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.12403765320777893},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.08329427242279053}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679222","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679222","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3627673.3679222","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679222","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2970476646","https://openalex.org/W3044438666","https://openalex.org/W3046375318","https://openalex.org/W3133702157","https://openalex.org/W4285210452","https://openalex.org/W4285231210","https://openalex.org/W4323655724","https://openalex.org/W4384895072","https://openalex.org/W4386246835","https://openalex.org/W4387162877","https://openalex.org/W4387346544","https://openalex.org/W4387848774","https://openalex.org/W4388994251","https://openalex.org/W4389518833"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"As":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"are":[5],"integrated":[6],"into":[7],"various":[8,86],"sectors,":[9],"ensuring":[10],"their":[11,25,46],"reliability":[12],"and":[13,21,27,65,123,181,203,226,251],"safety":[14],"is":[15,69,95,126,246],"crucial.":[16],"This":[17,244],"necessitates":[18],"rigorous":[19],"probing":[20],"auditing":[22,217,234,268],"to":[23,34,62,81,96,128,133,173,192,223],"maintain":[24],"effectiveness":[26],"trustworthiness":[28],"in":[29,45,88,114,262],"practical":[30,204],"applications.":[31],"Subjecting":[32],"LLMs":[33,87,219],"varied":[35],"iterations":[36],"of":[37,85,137,168,177,190,218,259],"a":[38,53,60,77,89,98,107,157,266],"single":[39,108,158],"query":[40],"can":[41],"unveil":[42],"potential":[43,178],"inconsistencies":[44,113],"knowledge":[47],"base":[48],"or":[49,118],"functional":[50],"capacity.":[51],"However,":[52],"tool":[54,79,245],"for":[55,241,248],"performing":[56],"such":[57],"audits":[58],"with":[59,196],"easy":[61],"execute":[63],"workflow,":[64],"low":[66],"technical":[67],"threshold":[68],"lacking.":[70],"In":[71],"this":[72,143],"demo,":[73],"we":[74],"introduce":[75],"\"AuditLLM,\"":[76],"novel":[78],"designed":[80],"audit":[82,97],"the":[83,115,138,152,163,188,197],"performance":[84],"methodical":[90],"way.":[91],"AuditLLM's":[92],"primary":[93],"function":[94],"given":[99],"LLM":[100,125,233],"by":[101,162,220,235],"deploying":[102],"multiple":[103,237],"probes":[104],"derived":[105],"from":[106],"question,":[109],"thus":[110],"detecting":[111],"any":[112],"model's":[116],"comprehension":[117],"performance.":[119],"A":[120,165],"robust,":[121],"reliable,":[122],"consistent":[124],"expected":[127],"generate":[129],"semantically":[130],"similar":[131],"responses":[132,222],"variably":[134],"phrased":[135],"versions":[136],"same":[139],"question.":[140],"Building":[141],"on":[142,156],"premise,":[144],"AuditLLM":[145,191,206],"generates":[146],"easily":[147],"interpretable":[148],"results":[149],"that":[150],"reflect":[151],"LLM's":[153],"consistency":[154],"based":[155],"input":[159],"question":[160],"provided":[161],"user.":[164],"certain":[166],"level":[167],"inconsistency":[169],"has":[170],"been":[171],"shown":[172],"be":[174],"an":[175],"indicator":[176],"bias,":[179],"hallucinations,":[180],"other":[182],"issues.":[183],"One":[184],"could":[185],"then":[186],"use":[187],"output":[189],"further":[193],"investigate":[194],"issues":[195],"aforementioned":[198],"LLM.":[199],"To":[200],"facilitate":[201],"demonstration":[202],"uses,":[205],"offers":[207],"two":[208],"key":[209],"modes:":[210],"(1)":[211],"Live":[212],"mode":[213,229],"which":[214,230],"allows":[215],"instant":[216],"analyzing":[221],"real-time":[224],"queries;":[225],"(2)":[227],"Batch":[228],"facilitates":[231],"comprehensive":[232],"processing":[236],"queries":[238],"at":[239],"once":[240],"in-depth":[242],"analysis.":[243],"beneficial":[247],"both":[249],"researchers":[250],"general":[252],"users,":[253],"as":[254],"it":[255],"enhances":[256],"our":[257],"understanding":[258],"LLMs'":[260],"capabilities":[261],"generating":[263],"responses,":[264],"using":[265],"standardized":[267],"platform.":[269]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}