{"id":"https://openalex.org/W4412888513","doi":"https://doi.org/10.18653/v1/2025.findings-acl.467","title":"Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data","display_name":"Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888513","doi":"https://doi.org/10.18653/v1/2025.findings-acl.467"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.467","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.467","pdf_url":"https://aclanthology.org/2025.findings-acl.467.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.467.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047620514","display_name":"Xin-Cheng Wen","orcid":"https://orcid.org/0000-0002-2115-9921"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin-Cheng Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054969834","display_name":"Yijun Yang","orcid":"https://orcid.org/0000-0002-9243-6228"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yijun Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Cuiyun Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cuiyun Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604658","display_name":"Yang Xiao","orcid":"https://orcid.org/0009-0005-8009-2252"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019789719","display_name":"Deheng Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deheng Ye","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":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8935","last_page":"8949"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9854999780654907,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9854999780654907,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9714000225067139,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.9503999948501587,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.6137840151786804},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6005752682685852},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5675665736198425},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5329880118370056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3825083374977112},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.15700727701187134},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11159497499465942},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.07510519027709961}],"concepts":[{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.6137840151786804},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6005752682685852},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5675665736198425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5329880118370056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3825083374977112},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.15700727701187134},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11159497499465942},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.07510519027709961}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.467","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.467","pdf_url":"https://aclanthology.org/2025.findings-acl.467.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.467","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.467","pdf_url":"https://aclanthology.org/2025.findings-acl.467.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2100943491","display_name":null,"funder_award_id":"62202462","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3616843134","display_name":null,"funder_award_id":"2023A1515011959","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G617086500","display_name":null,"funder_award_id":"62472126","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888513.pdf","grobid_xml":"https://content.openalex.org/works/W4412888513.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W2147697413","https://openalex.org/W2154063878","https://openalex.org/W4231274751","https://openalex.org/W2556012038"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"demonstrate":[4,157],"considerable":[5],"proficiency":[6],"in":[7,14,72,78,170],"numerous":[8],"codingrelated":[9],"tasks;":[10],"however,":[11],"their":[12,47],"capabilities":[13],"detecting":[15],"software":[16,165],"vulnerabilities":[17],"remain":[18],"limited.This":[19],"limitation":[20],"primarily":[21],"stems":[22],"from":[23],"two":[24],"factors:":[25],"(1)":[26],"the":[27,37,55,67,82,123,131,171],"absence":[28],"of":[29,69,84,125],"reasoning":[30,102,114,127],"data":[31,103],"related":[32],"to":[33,40,61,144],"vulnerabilities,":[34],"which":[35],"hinders":[36],"models'":[38],"ability":[39],"capture":[41],"underlying":[42],"vulnerability":[43,65,73,99,117,147,166],"patterns;":[44],"and":[45,105,112,118,154],"(2)":[46],"focus":[48],"on":[49,152],"learning":[50],"semantic":[51],"representations":[52],"rather":[53],"than":[54],"reason":[56],"behind":[57],"them,":[58],"thus":[59],"failing":[60],"recognize":[62],"semantically":[63],"similar":[64],"samples.Furthermore,":[66],"development":[68],"LLMs":[70],"specialized":[71],"detection":[74],"is":[75],"challenging,":[76],"particularly":[77],"environments":[79],"characterized":[80],"by":[81,136],"scarcity":[83],"high-quality":[85,126],"datasets.In":[86],"this":[87],"paper,":[88],"we":[89,109,129],"propose":[90],"a":[91],"novel":[92],"framework":[93],"ReVD":[94,143,159],"that":[95,158],"excels":[96],"at":[97],"mining":[98],"patterns":[100],"through":[101],"synthesizing":[104],"vulnerability-specific":[106],"preference":[107,139],"optimization.Specifically,":[108],"construct":[110],"forward":[111],"backward":[113],"processes":[115],"for":[116,141,163],"corresponding":[119],"fixed":[120],"code,":[121],"ensuring":[122],"synthesis":[124],"data.Moreover,":[128],"design":[130],"triplet":[132],"supervised":[133],"fine-tuning":[134],"followed":[135],"curriculum":[137],"online":[138],"optimization":[140],"enabling":[142],"better":[145],"understand":[146],"patterns.The":[148],"extensive":[149],"experiments":[150],"conducted":[151],"PrimeVul":[153],"SVEN":[155],"datasets":[156],"sets":[160],"new":[161],"state-of-the-art":[162],"LLM-based":[164],"detection,":[167],"e.g.,":[168],"12.24%-22.77%improvement":[169],"accuracy.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}