{"id":"https://openalex.org/W7166837923","doi":"https://doi.org/10.18653/v1/2026.findings-acl.683","title":"Beyond Superficial Tests: Adversarial Refinement for Reliable Property-Based Testing","display_name":"Beyond Superficial Tests: Adversarial Refinement for Reliable Property-Based Testing","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166837923","doi":"https://doi.org/10.18653/v1/2026.findings-acl.683"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.683","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.683","pdf_url":"https://aclanthology.org/2026.findings-acl.683.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 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.683.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139787233","display_name":"Xiao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033190349","display_name":"Runlin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Runlin Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139821120","display_name":"Zhe Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhe Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139797977","display_name":"Xiang Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139761513","display_name":"Hailong Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hailong Sun","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82748165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13957","last_page":"13974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.421099990606308,"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":0.421099990606308,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.11289999634027481,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.08720000088214874,"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/adversarial-system","display_name":"Adversarial system","score":0.6132000088691711},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.32760000228881836},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.2800999879837036},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2775999903678894},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.2775999903678894}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6132000088691711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5511999726295471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3977999985218048},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.683","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.683","pdf_url":"https://aclanthology.org/2026.findings-acl.683.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 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.683","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.683","pdf_url":"https://aclanthology.org/2026.findings-acl.683.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 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3324212921","display_name":null,"funder_award_id":"62472017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166837923.pdf","grobid_xml":"https://content.openalex.org/works/W7166837923.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4,148],"demonstrated":[5],"remarkable":[6],"proficiency":[7],"in":[8,47,107,144],"code":[9,40],"generation,":[10],"yet":[11],"their":[12],"application":[13],"to":[14,34,90,104,116,156],"Property-Based":[15],"Testing":[16],"(PBT)":[17],"remains":[18],"fraught":[19],"with":[20],"a":[21,52,80,87,112],"\"superficiality":[22],"gap\".While":[23],"LLMs":[24],"can":[25],"readily":[26],"generate":[27,92],"syntactically":[28],"correct":[29],"tests,":[30],"they":[31],"often":[32,120],"struggle":[33],"bridge":[35],"the":[36,101,108],"semantic":[37,114,159],"gap":[38],"between":[39],"implementation":[41],"and":[42],"its":[43,154],"intended":[44],"logic,":[45],"resulting":[46],"weak":[48],"properties":[49,68],"that":[50,65,99,127,147],"provide":[51],"false":[53],"sense":[54],"of":[55,82],"security.To":[56],"address":[57],"this,":[58],"we":[59],"introduce":[60],"PROBE,":[61],"an":[62],"agentic":[63],"framework":[64],"hardens":[66],"software":[67],"through":[69],"Adversarial":[70],"Refinement.Unlike":[71],"traditional":[72],"generation":[73,78],"approaches,":[74],"PROBE":[75,110,128,138],"treats":[76],"test":[77],"as":[79],"game":[81],"\"semantic":[83],"asymmetry\":":[84],"it":[85],"employs":[86],"Validator":[88],"agent":[89],"actively":[91],"counterimplementations,":[93],"which":[94],"are":[95],"semantically":[96],"incorrect":[97],"codes":[98],"satisfy":[100],"generated":[102],"property,":[103],"expose":[105],"loopholes":[106],"specification.Furthermore,":[109],"constructs":[111],"cross-function":[113],"graph":[115],"capture":[117],"deep":[118,158],"dependencies":[119],"missed":[121],"by":[122,132,151],"local":[123],"analysis.Extensive":[124],"evaluation":[125],"reveals":[126],"increases":[129],"mutation":[130],"scores":[131],"9.79%":[133],"over":[134],"baselines.In":[135],"real-world":[136],"deployment,":[137],"identified":[139],"45":[140],"previously":[141],"unknown":[142],"bugs":[143],"top-tier":[145],"libraries":[146],"been":[149],"confirmed":[150],"developers,":[152],"demonstrating":[153],"ability":[155],"uncover":[157],"defects.":[160]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}