{"id":"https://openalex.org/W6929315909","doi":"https://doi.org/10.48550/arxiv.2506.17647","title":"Improving Compiler Bug Isolation by Leveraging Large Language Models","display_name":"Improving Compiler Bug Isolation by Leveraging Large Language Models","publication_year":2025,"publication_date":"2025-06-21","ids":{"openalex":"https://openalex.org/W6929315909","doi":"https://doi.org/10.48550/arxiv.2506.17647"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.17647","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.17647","pdf_url":"https://arxiv.org/pdf/2506.17647","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.17647","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Qi, Yixian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Yixian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jiang, Jiajun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Jiajun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028873025","display_name":"Fengjie Li","orcid":"https://orcid.org/0009-0001-7137-3934","observed_orcids":["https://orcid.org/0009-0001-7137-3934"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Fengjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Bowen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Bowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Hongyu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hongyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Chen, Junjie","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Junjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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":true,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9932000041007996,"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"}},"topics":[{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9932000041007996,"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/T10260","display_name":"Software Engineering Research","score":0.006599999964237213,"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":0.0,"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/large-language-models","display_name":"large language models","score":0.9940000176429749},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.6919999718666077},{"id":"https://openalex.org/keywords/test-coverage-analysis","display_name":"test coverage analysis","score":0.6859999895095825},{"id":"https://openalex.org/keywords/gcc","display_name":"GCC","score":0.8790000081062317},{"id":"https://openalex.org/keywords/llvm","display_name":"LLVM","score":0.7889999747276306},{"id":"https://openalex.org/keywords/compiler-bugs","display_name":"compiler bugs","score":0.4830000102519989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8690999746322632},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8058000206947327},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6514000296592712},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.4941999912261963},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.41850000619888306},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.36410000920295715},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.26910001039505005},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C68366613","wikidata":"https://www.wikidata.org/wiki/Q5156378","display_name":"Compiler correctness","level":3,"score":0.2467000037431717},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.24660000205039978},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.23649999499320984},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.23569999635219574},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2298000007867813},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.22769999504089355},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.2231999933719635},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2207999974489212},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.21879999339580536},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2160000056028366},{"id":"https://openalex.org/C131275738","wikidata":"https://www.wikidata.org/wiki/Q7445023","display_name":"Security bug","level":5,"score":0.2117999941110611},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.21070000529289246},{"id":"https://openalex.org/C2779639559","wikidata":"https://www.wikidata.org/wiki/Q7661178","display_name":"Symbolic execution","level":3,"score":0.20659999549388885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20600000023841858},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.20559999346733093},{"id":"https://openalex.org/C148027188","wikidata":"https://www.wikidata.org/wiki/Q907375","display_name":"Unit testing","level":3,"score":0.20020000636577606},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.19920000433921814},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.19869999587535858},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.19760000705718994},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.19689999520778656},{"id":"https://openalex.org/C9957790","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler construction","level":3,"score":0.1882999986410141},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.18709999322891235},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.18690000474452972},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.1834000051021576},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.1808999925851822},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.18039999902248383}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.17647","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.17647","pdf_url":"https://arxiv.org/pdf/2506.17647","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.17647","doi":"https://doi.org/10.48550/arxiv.2506.17647","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.17647","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.17647","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.17647","pdf_url":"https://arxiv.org/pdf/2506.17647","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.6059616208076477}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Compilers":[0],"play":[1],"a":[2,130],"foundational":[3],"role":[4],"in":[5,48,90,129,176,193],"building":[6],"reliable":[7],"software":[8],"systems,":[9],"and":[10,52,82,145,155,166,173],"bugs":[11,150,169],"within":[12],"them":[13],"can":[14],"lead":[15],"to":[16,35,77,87],"catastrophic":[17],"consequences.":[18],"The":[19],"compilation":[20,122],"process":[21],"typically":[22],"involves":[23],"hundreds":[24],"of":[25,60,100,111,133,138,190],"files,":[26],"making":[27],"traditional":[28],"automated":[29],"bug":[30,43],"isolation":[31],"techniques":[32,45],"inapplicable":[33],"due":[34],"scalability":[36],"or":[37],"effectiveness":[38],"issues.":[39],"Current":[40],"mainstream":[41],"compiler":[42,79],"localization":[44],"have":[46],"limitations":[47],"test":[49,104,117],"program":[50],"mutation":[51],"resource":[53],"consumption.":[54],"Inspired":[55],"by":[56],"the":[57,102,152,177,184,188],"recent":[58],"advances":[59],"pre-trained":[61],"Large":[62],"Language":[63],"Models":[64],"(LLMs),":[65],"we":[66],"propose":[67],"an":[68],"innovative":[69],"approach":[70,96],"named":[71],"AutoCBI,":[72],"which":[73],"(1)":[74],"uses":[75],"LLMs":[76],"summarize":[78],"file":[80,93,107],"functions":[81],"(2)":[83],"employs":[84],"specialized":[85],"prompts":[86],"guide":[88],"LLM":[89],"reordering":[91],"suspicious":[92,112,134],"rankings.":[94],"This":[95],"leverages":[97],"four":[98],"types":[99],"information:":[101],"failing":[103],"program,":[105],"source":[106],"function":[108],"summaries,":[109],"lists":[110],"files":[113],"identified":[114],"through":[115],"analyzing":[116],"coverage,":[118],"as":[119,121],"well":[120],"configurations":[123],"with":[124],"related":[125],"output":[126],"messages,":[127],"resulting":[128],"refined":[131],"ranking":[132],"files.":[135],"Our":[136],"evaluation":[137],"AutoCBI":[139,162],"against":[140],"state-of-the-art":[141],"approaches":[142],"(DiWi,":[143],"RecBi":[144],"FuseFL)":[146],"on":[147],"120":[148],"real-world":[149],"from":[151],"widely-used":[153],"GCC":[154],"LLVM":[156],"compilers":[157],"demonstrates":[158],"its":[159],"effectiveness.":[160],"Specifically,":[161],"isolates":[163],"66.67%/69.23%,":[164],"300%/340%,":[165],"100%/57.14%":[167],"more":[168],"than":[170],"RecBi,":[171],"DiWi,":[172],"FuseFL,":[174],"respectively,":[175],"Top-1":[178],"ranked":[179],"results":[180],"for":[181],"GCC/LLVM.":[182],"Additionally,":[183],"ablation":[185],"study":[186],"underscores":[187],"significance":[189],"each":[191],"component":[192],"our":[194],"approach.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2025-10-10T00:00:00"}
