{"id":"https://openalex.org/W4411449803","doi":"https://doi.org/10.1145/3729356","title":"A Knowledge Enhanced Large Language Model for Bug Localization","display_name":"A Knowledge Enhanced Large Language Model for Bug Localization","publication_year":2025,"publication_date":"2025-06-19","ids":{"openalex":"https://openalex.org/W4411449803","doi":"https://doi.org/10.1145/3729356"},"language":"en","primary_location":{"id":"doi:10.1145/3729356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729356","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3729356","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065206946","display_name":"Yue Li","orcid":"https://orcid.org/0000-0002-1856-7182"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yue Li","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103126336","display_name":"Bohan Liu","orcid":"https://orcid.org/0000-0002-0146-5411"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohan Liu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458319","display_name":"Ting Zhang","orcid":"https://orcid.org/0000-0002-6001-1372"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ting Zhang","raw_affiliation_strings":["Singapore Management University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102846748","display_name":"Zhiqi Wang","orcid":"https://orcid.org/0009-0004-8029-4607"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqi Wang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081036622","display_name":"David Lo","orcid":"https://orcid.org/0000-0002-4367-7201"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"David Lo","raw_affiliation_strings":["Singapore Management University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030814744","display_name":"Lanxin Yang","orcid":"https://orcid.org/0000-0002-0406-2263"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanxin Yang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080124436","display_name":"Jun Lyu","orcid":"https://orcid.org/0000-0001-9070-7269"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Lyu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100420137","display_name":"He Zhang","orcid":"https://orcid.org/0000-0002-9159-5331"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Zhang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5065206946"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":6.3055,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.96092076,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"2","issue":"FSE","first_page":"1914","last_page":"1936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.982699990272522,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9805999994277954,"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/computer-science","display_name":"Computer science","score":0.7190775871276855},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5154205560684204},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49164849519729614},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4449123740196228},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40990549325942993},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3806436061859131},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3373446464538574},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3273236155509949}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7190775871276855},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5154205560684204},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49164849519729614},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4449123740196228},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40990549325942993},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3806436061859131},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3373446464538574},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3273236155509949},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3729356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729356","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-11892","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/10890","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"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":"https://doi.org/10.1145/3729356","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1145/3729356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729356","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2483327705","https://openalex.org/W2606092111","https://openalex.org/W2608239929","https://openalex.org/W2614846107","https://openalex.org/W2615497679","https://openalex.org/W2757101400","https://openalex.org/W2891728317","https://openalex.org/W2899575547","https://openalex.org/W2949266019","https://openalex.org/W2983102021","https://openalex.org/W2999854190","https://openalex.org/W3014521650","https://openalex.org/W3038598309","https://openalex.org/W3151929433","https://openalex.org/W3158302971","https://openalex.org/W3198659451","https://openalex.org/W4233179804","https://openalex.org/W4233730851","https://openalex.org/W4239249613","https://openalex.org/W4298156464","https://openalex.org/W4299527668","https://openalex.org/W4309400067","https://openalex.org/W4321497407","https://openalex.org/W4377707837","https://openalex.org/W4380738578","https://openalex.org/W4386275705"],"related_works":["https://openalex.org/W2112835755","https://openalex.org/W4291951920","https://openalex.org/W2349674371","https://openalex.org/W2097495471","https://openalex.org/W1696545756","https://openalex.org/W2952827811","https://openalex.org/W2056202066","https://openalex.org/W2963262648","https://openalex.org/W4301867002","https://openalex.org/W2056790378"],"abstract_inverted_index":{"A":[0],"significant":[1],"number":[2],"of":[3,96,160,202,229,249,270,286],"bug":[4,25,44,68,129,212,290],"reports":[5,26,69],"are":[6,41,76,94],"generated":[7],"every":[8],"day":[9],"as":[10,88],"software":[11,49,207],"systems":[12],"continue":[13],"to":[14,23,30,63,78,84,178,225,251,254,272,282],"develop.":[15],"Large":[16],"Language":[17],"Models":[18],"(LLMs)":[19],"have":[20,56],"been":[21],"used":[22],"correlate":[24],"with":[27,209,215,239],"source":[28,71,171],"code":[29,148,151],"locate":[31],"bugs":[32],"automatically.":[33],"The":[34,274],"existing":[35],"research":[36],"has":[37],"shown":[38],"that":[39,93,139,154,277],"LLMs":[40],"effective":[42],"for":[43,128],"localization":[45],"and":[46,70,122,135,170,184,190,236],"can":[47,155],"increase":[48],"development":[50],"efficiency.":[51],"However,":[52],"these":[53,60,74,105],"studies":[54],"still":[55],"two":[57],"limitations.":[58],"First,":[59],"models":[61,75],"fail":[62],"capture":[64],"context":[65],"information":[66,90,138,143,153],"about":[67,144],"code.":[72,172],"Second,":[73],"unable":[77],"understand":[79],"the":[80,157,179,216,240,255,284,287],"domain-specific":[81],"expertise":[82],"inherent":[83],"particular":[85],"projects,":[86],"such":[87],"version":[89],"in":[91,227,289],"projects":[92,208],"composed":[95],"alphanumeric":[97],"characters":[98],"without":[99],"any":[100],"semantic":[101,142,152],"meaning.":[102],"To":[103,194],"address":[104],"challenges,":[106],"we":[107,163,174,198],"propose":[108],"a":[109,200],"K":[110],"nowledge":[111],"E":[112],"nhanced":[113],"P":[114],"re-":[115],"T":[116],"rained":[117],"model":[118,218],"using":[119],"project":[120,137,168],"documents":[121,132,169],"historical":[123],"code,":[124],"called":[125,262],"KEPT":[126,220,245,265],",":[127,264],"localization.":[130,291],"Project":[131],"record,":[133],"revise,":[134],"restate":[136],"provides":[140],"rich":[141,150],"those":[145],"projects.":[146],"Historical":[147],"contains":[149],"enhance":[156,283],"reasoning":[158,192],"ability":[159],"LLMs.":[161],"Specifically,":[162],"construct":[164],"knowledge":[165,176,279],"graphs":[166,177,280],"from":[167],"Then,":[173],"introduce":[175],"LLM":[180,243,258,288],"through":[181],"soft-position":[182],"embedding":[183],"visible":[185],"matrices,":[186],"enhancing":[187],"its":[188],"contextual":[189],"professional":[191],"ability.":[193],"validate":[195],"our":[196],"model,":[197],"conducted":[199],"series":[201],"experiments":[203],"on":[204],"seven":[205],"open-source":[206],"over":[210],"6,000":[211],"reports.":[213],"Compared":[214,238,253],"traditional":[217],"(Locus),":[219],"performs":[221],"better":[222],"by":[223,260],"33.2%":[224],"59.5%":[226],"terms":[228],"mean":[230,233],"reciprocal":[231],"rank,":[232],"average":[234,268],"precision,":[235],"Top@N.":[237],"best-performing":[241],"non-commercial":[242],"(CodeT5),":[244],"achieves":[246,266],"an":[247,267],"improvement":[248,269],"36.6%":[250],"63.7%.":[252],"state-of-the-art":[256],"commercial":[257],"developed":[259],"OpenAI,":[261],"text-embedding-ada-002":[263],"7.8%":[271],"17.4%.":[273],"results":[275],"indicate":[276],"introducing":[278],"contributes":[281],"effectiveness":[285]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
