{"id":"https://openalex.org/W4416233727","doi":"https://doi.org/10.1109/issre66568.2025.00039","title":"Enhancing Reliability Assurance for DNN against Numerical Defect with Large Language Models","display_name":"Enhancing Reliability Assurance for DNN against Numerical Defect with Large Language Models","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4416233727","doi":"https://doi.org/10.1109/issre66568.2025.00039"},"language":null,"primary_location":{"id":"doi:10.1109/issre66568.2025.00039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/issre66568.2025.00039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 36th International Symposium on Software Reliability Engineering (ISSRE)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100329183","display_name":"Jinyu Liu","orcid":"https://orcid.org/0000-0003-0233-3493"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyu Liu","raw_affiliation_strings":["Beihang University,School of Reliability and Systems Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,School of Reliability and Systems Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110953265","display_name":"Jun Ai","orcid":"https://orcid.org/0009-0007-5530-0608"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Ai","raw_affiliation_strings":["Beihang University,School of Reliability and Systems Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,School of Reliability and Systems Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101486101","display_name":"Haoran Su","orcid":"https://orcid.org/0009-0002-9507-6544"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Su","raw_affiliation_strings":["Beihang University,School of Reliability and Systems Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,School of Reliability and Systems Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073264631","display_name":"Tao Shi","orcid":"https://orcid.org/0000-0003-2867-8158"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Shi","raw_affiliation_strings":["Beihang University,School of Reliability and Systems Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,School of Reliability and Systems Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"300","last_page":"310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.91839998960495,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.91839998960495,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.011099999770522118,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.00559999980032444,"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/debugging","display_name":"Debugging","score":0.7591999769210815},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.7128999829292297},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5514000058174133},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5224999785423279},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.519599974155426},{"id":"https://openalex.org/keywords/static-analysis","display_name":"Static analysis","score":0.4916999936103821},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49149999022483826},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4758000075817108}],"concepts":[{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.7591999769210815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7555000185966492},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.7128999829292297},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5514000058174133},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.5307000279426575},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5224999785423279},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.519599974155426},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.4916999936103821},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49149999022483826},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4758000075817108},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C91071405","wikidata":"https://www.wikidata.org/wiki/Q1413145","display_name":"Program slicing","level":3,"score":0.4311999976634979},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3714999854564667},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36629998683929443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3634999990463257},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3127000033855438},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29899999499320984},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.2935999929904938},{"id":"https://openalex.org/C2779639559","wikidata":"https://www.wikidata.org/wiki/Q7661178","display_name":"Symbolic execution","level":3,"score":0.27959999442100525},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.2671000063419342},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C48753275","wikidata":"https://www.wikidata.org/wiki/Q11216","display_name":"Numerical analysis","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.26100000739097595}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/issre66568.2025.00039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/issre66568.2025.00039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 36th International Symposium on Software Reliability Engineering (ISSRE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2850992922","https://openalex.org/W2968594320","https://openalex.org/W3005780259","https://openalex.org/W3090643686","https://openalex.org/W3109004940","https://openalex.org/W3195618452","https://openalex.org/W4312629101","https://openalex.org/W4313547562","https://openalex.org/W4384026546"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"Neural":[1],"Networks":[2],"(DNNs)":[3],"are":[4],"increasingly":[5],"deployed":[6],"in":[7,53,131],"safety-critical":[8],"systems,":[9],"yet":[10],"their":[11,44,50],"numerical":[12,97,149,161],"reliability":[13,143],"remains":[14],"a":[15,64,108,138,159],"pressing":[16],"concern":[17],"due":[18],"to":[19,36,86],"defects":[20,98],"like":[21],"NaN/INF":[22],"occurrences":[23],"during":[24],"training/inference.":[25],"Existing":[26],"static":[27,75,125,148],"analyzers":[28],"detect":[29],"operator-level":[30,41,96],"risks":[31],"but":[32,127],"lack":[33],"the":[34,91,112,147,152],"ability":[35],"establish":[37],"contextual":[38],"mappings":[39],"between":[40],"anomalies":[42],"and":[43],"originating":[45],"code":[46],"implementations,":[47],"thereby":[48],"limiting":[49],"practical":[51,160],"applicability":[52],"real-world":[54,110],"debugging":[55],"scenarios.":[56],"To":[57],"address":[58],"this":[59,61],"limitation,":[60],"paper":[62],"introduces":[63],"novel":[65],"hybrid":[66],"method":[67,93,114],"that":[68],"synergizes":[69],"risk":[70],"sensitive":[71],"paths":[72],"derived":[73],"from":[74],"analysis":[76,150,163],"with":[77,99,151],"Large":[78],"Language":[79],"Model(LLM)-guided":[80],"semantic":[81,153],"reasoning.":[82],"By":[83],"anchoring":[84],"LLMs":[85],"identified":[87],"risk-sensitive":[88],"computation":[89],"paths,":[90],"proposed":[92,113],"precisely":[94],"correlates":[95],"code-level":[100,132],"vulnerabilities,":[101],"while":[102],"mitigating":[103],"LLM":[104],"hallucinations.":[105],"Evaluated":[106],"on":[107],"widely-used":[109],"benchmark,":[111],"achieves":[115],"$\\mathbf{1":[116],"0":[117],"0}":[118],"\\boldsymbol{\\%}$":[119],"defect":[120,162],"detection":[121],"accuracy,":[122],"matching":[123],"state-of-the-art":[124],"analyzers,":[126],"significantly":[128],"outperforms":[129],"them":[130],"root-cause":[133],"localization.":[134],"This":[135],"work":[136],"pioneers":[137],"new":[139],"paradigm":[140],"for":[141],"DNN":[142],"assurance":[144],"by":[145],"combining":[146],"reasoning":[154],"power":[155],"of":[156],"LLMs,":[157],"establishing":[158],"pipeline.":[164]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-13T00:00:00"}