{"id":"https://openalex.org/W4399795583","doi":"https://doi.org/10.48550/arxiv.2406.10279","title":"We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs","display_name":"We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs","publication_year":2024,"publication_date":"2024-06-12","ids":{"openalex":"https://openalex.org/W4399795583","doi":"https://doi.org/10.48550/arxiv.2406.10279"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.10279","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.10279","pdf_url":"https://arxiv.org/pdf/2406.10279","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,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.10279","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099241648","display_name":"Joseph Spracklen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45438204","display_name":"The University of Texas at San Antonio","ror":"https://ror.org/01kd65564","country_code":"US","type":"education","lineage":["https://openalex.org/I45438204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Spracklen, Joseph","raw_affiliation_strings":["University of Texas at San Antonio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at San Antonio","institution_ids":["https://openalex.org/I45438204"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089338879","display_name":"Raveen Wijewickrama","orcid":"https://orcid.org/0000-0002-3718-7847","observed_orcids":["https://orcid.org/0000-0002-3718-7847"]},"institutions":[{"id":"https://openalex.org/I45438204","display_name":"The University of Texas at San Antonio","ror":"https://ror.org/01kd65564","country_code":"US","type":"education","lineage":["https://openalex.org/I45438204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wijewickrama, Raveen","raw_affiliation_strings":["University of Texas at San Antonio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at San Antonio","institution_ids":["https://openalex.org/I45438204"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099241649","display_name":"A. H. M. Nazmus Sakib","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sakib, A H M Nazmus","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045020872","display_name":"Anindya Maiti","orcid":"https://orcid.org/0000-0001-6461-2805","observed_orcids":["https://orcid.org/0000-0001-6461-2805"]},"institutions":[{"id":"https://openalex.org/I8692664","display_name":"University of Oklahoma","ror":"https://ror.org/02aqsxs83","country_code":"US","type":"education","lineage":["https://openalex.org/I8692664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maiti, Anindya","raw_affiliation_strings":["University of Oklahoma"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oklahoma","institution_ids":["https://openalex.org/I8692664"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Viswanath, Bimal","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viswanath, Bimal","raw_affiliation_strings":["Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jadliwala, Murtuza","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45438204","display_name":"The University of Texas at San Antonio","ror":"https://ror.org/01kd65564","country_code":"US","type":"education","lineage":["https://openalex.org/I45438204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jadliwala, Murtuza","raw_affiliation_strings":["University of Texas at San Antonio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at San Antonio","institution_ids":["https://openalex.org/I45438204"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":52,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9721999764442444,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.9721999764442444,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.02160000056028366,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.0012000000569969416,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/code-generation","display_name":"code generation","score":0.49399998784065247},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9929999709129333},{"id":"https://openalex.org/keywords/software-supply-chain-security","display_name":"software supply chain security","score":0.9760000109672546},{"id":"https://openalex.org/keywords/open-source-software","display_name":"open source software","score":0.6629999876022339},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.8889999985694885},{"id":"https://openalex.org/keywords/python","display_name":"Python","score":0.4269999861717224},{"id":"https://openalex.org/keywords/javascript","display_name":"JavaScript","score":0.9369999766349792}],"concepts":[{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6683372259140015},{"id":"https://openalex.org/C3020349426","wikidata":"https://www.wikidata.org/wiki/Q207822","display_name":"Package design","level":2,"score":0.49896240234375},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.48303064703941345},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.38641878962516785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3584980368614197},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28861433267593384},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1433757245540619},{"id":"https://openalex.org/C117671659","wikidata":"https://www.wikidata.org/wiki/Q11049265","display_name":"Manufacturing engineering","level":1,"score":0.1013462245464325},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.10279","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.10279","pdf_url":"https://arxiv.org/pdf/2406.10279","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,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.10279","doi":"https://doi.org/10.48550/arxiv.2406.10279","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.10279","pdf_url":null,"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,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.10279","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.10279","pdf_url":"https://arxiv.org/pdf/2406.10279","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,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G453738070","display_name":"SaTC: CORE: Small: Systematic Threat Characterization and Prevention in Open-Domain Dialog Systems","funder_award_id":"2231002","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310677","display_name":"University of Texas at San Antonio","ror":"https://ror.org/01kd65564"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399795583.pdf","grobid_xml":"https://content.openalex.org/works/W4399795583.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W3177813494","https://openalex.org/W4320836790","https://openalex.org/W4327810158","https://openalex.org/W4376312605","https://openalex.org/W4378506863","https://openalex.org/W4384918448","https://openalex.org/W4387561528","https://openalex.org/W4389364446","https://openalex.org/W4390602555","https://openalex.org/W4390723197","https://openalex.org/W4391272793","https://openalex.org/W4399528455","https://openalex.org/W4402670020","https://openalex.org/W4404534210","https://openalex.org/W4404711543","https://openalex.org/W6941323178","https://openalex.org/W7125637239"],"related_works":["https://openalex.org/W4407090931","https://openalex.org/W7223209237","https://openalex.org/W7171488176","https://openalex.org/W7204189675","https://openalex.org/W7161692241","https://openalex.org/W7125947608","https://openalex.org/W4416096812","https://openalex.org/W7167244437","https://openalex.org/W7162785405","https://openalex.org/W7164021702"],"abstract_inverted_index":{"The":[0],"reliance":[1],"of":[2,22,33,58,70,83,98,105,115,153,174,184,208],"popular":[3,120],"programming":[4,88,137],"languages":[5,138],"such":[6],"as":[7,222],"Python":[8],"and":[9,15,80,91,100,110,125,163,182,197,217,225,235],"JavaScript":[10],"on":[11],"centralized":[12],"package":[13,40,59,84,108,143,176,209,220],"repositories":[14],"open-source":[16,166],"software,":[17],"combined":[18],"with":[19],"the":[20,36,68,71,103,112,150,180,206,241],"emergence":[21],"code-generating":[23],"Large":[24],"Language":[25],"Models":[26],"(LLMs),":[27],"has":[28],"created":[29],"a":[30,55,64,78,95,169,223,236],"new":[31],"type":[32],"threat":[34,66],"to":[35,67,203],"software":[37,72],"supply":[38,73],"chain:":[39],"hallucinations.":[41,144],"These":[42],"hallucinations,":[43],"which":[44,239],"arise":[45],"from":[46],"fact-conflicting":[47],"errors":[48],"when":[49],"generating":[50,106],"code":[51,123,133,213,233],"using":[52,229],"LLMs,":[53],"represent":[54],"novel":[56],"form":[57],"confusion":[60],"attack":[61],"that":[62,139,148,149,199],"poses":[63],"critical":[65],"integrity":[69],"chain.":[74],"This":[75],"paper":[76],"conducts":[77],"rigorous":[79],"comprehensive":[81],"evaluation":[82],"hallucinations":[85,210,221],"across":[86],"different":[87],"languages,":[89],"settings,":[90],"parameters,":[92],"exploring":[93],"how":[94],"diverse":[96],"set":[97],"models":[99,162],"configurations":[101],"affect":[102],"likelihood":[104],"erroneous":[107],"recommendations":[109],"identifying":[111],"root":[113],"causes":[114],"this":[116,185,189],"phenomenon.":[117],"Using":[118],"16":[119],"LLMs":[121,231],"for":[122,142,160,165,232],"generation":[124],"two":[126,136],"unique":[127,172],"prompt":[128],"datasets,":[129],"we":[130,140,191],"generate":[131],"576,000":[132],"samples":[134],"in":[135],"analyze":[141],"Our":[145,215],"findings":[146,218],"reveal":[147],"average":[151],"percentage":[152],"hallucinated":[154,175],"packages":[155],"is":[156],"at":[157],"least":[158],"5.2%":[159],"commercial":[161],"21.7%":[164],"models,":[167],"including":[168],"staggering":[170],"205,474":[171],"examples":[173],"names,":[177],"further":[178],"underscoring":[179],"severity":[181],"pervasiveness":[183],"threat.":[186],"To":[187],"overcome":[188],"problem,":[190],"implement":[192],"several":[193],"hallucination":[194],"mitigation":[195],"strategies":[196],"show":[198],"they":[200],"are":[201],"able":[202],"significantly":[204],"reduce":[205],"number":[207],"while":[211,228],"maintaining":[212],"quality.":[214],"experiments":[216],"highlight":[219],"persistent":[224],"systemic":[226],"phenomenon":[227],"state-of-the-art":[230],"generation,":[234],"significant":[237],"challenge":[238],"deserves":[240],"research":[242],"community's":[243],"urgent":[244],"attention.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":30},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2024-06-19T00:00:00"}
