{"id":"https://openalex.org/W6888016194","doi":"https://doi.org/10.18420/inf2024_124","title":"Bug Detection and Localization using Pre-trained Code Language Models","display_name":"Bug Detection and Localization using Pre-trained Code Language Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W6888016194","doi":"https://doi.org/10.18420/inf2024_124"},"language":"en","primary_location":{"id":"doi:10.18420/inf2024_124","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2024_124","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"article-journal"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.18420/inf2024_124","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Campos, Viola","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Campos, Viola","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4426,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92106808,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.6438000202178955,"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":0.6438000202178955,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.25690001249313354,"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"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.014299999922513962,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/source-code","display_name":"Source code","score":0.6534000039100647},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6209999918937683},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6031000018119812},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5724999904632568},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5048999786376953},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4900999963283539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986999750137329},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6534000039100647},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6209999918937683},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6031000018119812},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5724999904632568},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4900999963283539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4860000014305115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48240000009536743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4458000063896179},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4156000018119812},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.40149998664855957},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C2986567400","wikidata":"https://www.wikidata.org/wiki/Q15777","display_name":"C programming language","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.2612000107765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18420/inf2024_124","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2024_124","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18420/inf2024_124","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2024_124","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"article-journal"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.562985897064209,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Language":[0,14],"models":[1,18,143],"for":[2,90,121],"source":[3,76],"code":[4,25,37,42,92],"have":[5],"improved":[6],"significantly":[7],"with":[8,112],"the":[9,55,138,172],"emergence":[10],"of":[11,24,141,157],"Transformer-based":[12],"Large":[13],"Models":[15],"(LLMs).":[16],"These":[17],"are":[19,29,133],"trained":[20],"on":[21,95,152,175],"large":[22],"amounts":[23],"in":[26,75,108],"which":[27],"defects":[28],"relatively":[30],"rare,":[31],"causing":[32],"them":[33],"to":[34,70,85,114,160],"perceive":[35],"faulty":[36,91],"as":[38,43,66,130,171],"unlikely":[39],"and":[40,72,144],"correct":[41],"more":[44],"'natural,'":[45],"thus":[46,145],"assigning":[47],"it":[48],"a":[49,67,87,109,153],"higher":[50],"likelihood.":[51],"We":[52],"hypothesize":[53],"that":[54,101,165],"likelihood":[56],"scores":[57],"generated":[58],"by":[59],"an":[60,169],"LLM":[61,96],"can":[62,104],"be":[63],"directly":[64,120],"used":[65],"lightweight":[68],"approach":[69],"detect":[71,105],"localize":[73],"bugs":[74],"code.":[77],"In":[78],"this":[79],"study,":[80],"we":[81,163],"evaluate":[82],"various":[83],"methods":[84,103,107],"construct":[86],"suspiciousness":[88],"score":[89],"segments":[93],"based":[94],"likelihoods.":[97],"Our":[98],"results":[99,174],"demonstrate":[100],"these":[102],"buggy":[106],"common":[110,131],"benchmark":[111],"up":[113],"78%":[115],"accuracy.":[116],"However,":[117],"using":[118],"LLMs":[119],"fault":[122],"localization":[123],"raises":[124],"concerns":[125],"about":[126],"training":[127,139],"data":[128,140],"leakage,":[129],"benchmarks":[132],"often":[134],"already":[135],"incorporated":[136],"into":[137],"such":[142],"learned.":[146],"By":[147],"additionally":[148],"evaluating":[149],"our":[150],"experiments":[151],"small,":[154],"non-public":[155],"dataset":[156],"student":[158],"submissions":[159],"programming":[161],"exercises,":[162],"show":[164],"leakage":[166],"is":[167],"indeed":[168],"issue,":[170],"evaluation":[173],"both":[176],"datasets":[177],"differ":[178],"significantly.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}