{"id":"https://openalex.org/W7135132372","doi":"https://doi.org/10.1109/icsrs68021.2025.11422208","title":"Automating Quality Assessment of LLM-Generated Defeaters","display_name":"Automating Quality Assessment of LLM-Generated Defeaters","publication_year":2025,"publication_date":"2025-11-26","ids":{"openalex":"https://openalex.org/W7135132372","doi":"https://doi.org/10.1109/icsrs68021.2025.11422208"},"language":null,"primary_location":{"id":"doi:10.1109/icsrs68021.2025.11422208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsrs68021.2025.11422208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 9th International Conference on System Reliability and Safety (ICSRS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2607.06039","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107068014","display_name":"Tihomir Rohlinger","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141254","display_name":"Fraunhofer Project Centre Wolfsburg","ror":"https://ror.org/03jgt3n70","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210141254","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tihomir Rohlinger","raw_affiliation_strings":["University of Stuttgart, Cariad SE,Empirical Software Engineering,Wolfsburg,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart, Cariad SE,Empirical Software Engineering,Wolfsburg,Germany","institution_ids":["https://openalex.org/I4210141254"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085769561","display_name":"Daniel Ratiu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141254","display_name":"Fraunhofer Project Centre Wolfsburg","ror":"https://ror.org/03jgt3n70","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210141254","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Ratiu","raw_affiliation_strings":["Process Methods and Tools Cariad SE,Wolfsburg,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Process Methods and Tools Cariad SE,Wolfsburg,Germany","institution_ids":["https://openalex.org/I4210141254"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128904034","display_name":"Stefan Wagner","orcid":null},"institutions":[{"id":"https://openalex.org/I41121874","display_name":"Heilbronn University","ror":"https://ror.org/04g5gcg95","country_code":"DE","type":"education","lineage":["https://openalex.org/I41121874"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wagner","raw_affiliation_strings":["Technical University of Munich,Chair of Software Engineering,Heilbronn,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Chair of Software Engineering,Heilbronn,Germany","institution_ids":["https://openalex.org/I41121874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.77624434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13295","display_name":"Safety Systems Engineering in Autonomy","score":0.7807000279426575,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13295","display_name":"Safety Systems Engineering in Autonomy","score":0.7807000279426575,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.09619999676942825,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.01489999983459711,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.6682999730110168},{"id":"https://openalex.org/keywords/quality-assurance","display_name":"Quality assurance","score":0.633400022983551},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.609000027179718},{"id":"https://openalex.org/keywords/automotive-industry","display_name":"Automotive industry","score":0.5192000269889832},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4749000072479248},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4253999888896942},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4180000126361847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6739000082015991},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.6682999730110168},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.633400022983551},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.609000027179718},{"id":"https://openalex.org/C526921623","wikidata":"https://www.wikidata.org/wiki/Q190117","display_name":"Automotive industry","level":2,"score":0.5192000269889832},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4253999888896942},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3903000056743622},{"id":"https://openalex.org/C3019060180","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automated method","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3472999930381775},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3273000121116638},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3124000132083893},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C51687143","wikidata":"https://www.wikidata.org/wiki/Q295600","display_name":"QA/QC","level":5,"score":0.2946000099182129},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icsrs68021.2025.11422208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsrs68021.2025.11422208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 9th International Conference on System Reliability and Safety (ICSRS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2607.06039","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.06039","pdf_url":"https://arxiv.org/pdf/2607.06039","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,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2607.06039","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.06039","pdf_url":"https://arxiv.org/pdf/2607.06039","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,"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":[{"score":0.5766447186470032,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7135132372.pdf","grobid_xml":"https://content.openalex.org/works/W7135132372.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1928755576","https://openalex.org/W2101210369","https://openalex.org/W2101234009","https://openalex.org/W2148143831","https://openalex.org/W3110281108","https://openalex.org/W4385245566","https://openalex.org/W4386585696","https://openalex.org/W4387143094","https://openalex.org/W4389158536","https://openalex.org/W4391770063","https://openalex.org/W4399577082","https://openalex.org/W4400337461","https://openalex.org/W4402339685","https://openalex.org/W4402339808","https://openalex.org/W4404953002","https://openalex.org/W4404953035","https://openalex.org/W4406788559"],"related_works":[],"abstract_inverted_index":{"High-integrity":[0],"systems,":[1],"such":[2,57],"as":[3,17,44],"autonomous":[4],"vehicle":[5],"fleets":[6],"or":[7],"large-scale":[8],"energy":[9,117],"infrastructures,":[10],"rely":[11],"on":[12,101],"structured":[13],"assurance":[14,91,176],"cases,":[15],"represented":[16],"rooted":[18],"directed":[19],"acyclic":[20],"graphs":[21,93],"(DAGs),":[22],"to":[23,168],"justify":[24],"safety":[25],"claims.":[26],"To":[27],"remain":[28],"valid":[29],"in":[30,113],"the":[31,114,170],"face":[32],"of":[33,56,90,154,175],"change,":[34],"these":[35],"cases":[36],"must":[37],"be":[38],"robust":[39],"against":[40],"potential":[41],"challenges,":[42],"known":[43],"\u2018defeaters\u2019.":[45],"While":[46],"large":[47],"language":[48,81],"models":[49],"(LLMs)":[50],"have":[51],"recently":[52],"enabled":[53],"scalable":[54],"generation":[55],"defeaters,":[58],"validating":[59],"their":[60],"quality":[61],"remains":[62],"a":[63],"predominantly":[64],"manual":[65],"and":[66,98,116],"subjective":[67,159],"process.":[68],"This":[69],"paper":[70],"presents":[71],"an":[72,151],"automated":[73,135],"method":[74,108,149],"for":[75,173],"assessing":[76],"LLM-generated":[77],"defeaters":[78],"using":[79,123],"natural":[80],"processing":[82],"(NLP)":[83],"techniques.":[84],"Our":[85,134,165],"approach":[86,136,166],"combines":[87],"structural":[88],"analysis":[89],"case":[92,111,177],"with":[94,140],"vector-based":[95],"semantic":[96],"embeddings":[97],"meta-classifiers":[99],"trained":[100],"expert-assessed":[102],"consensus":[103],"defeaters.":[104],"We":[105],"evaluate":[106],"our":[107],"through":[109,161],"two":[110],"studies":[112],"automotive":[115],"domains,":[118],"quantifying":[119],"human":[120],"reviewer":[121],"dissensus":[122],"Cohen\u2019s":[124],"kappa":[125],"($\\kappa":[126,144],"\\lt":[127],"0.442$),":[128],"which":[129],"indicates":[130],"low":[131],"inter-rater":[132],"agreement.":[133],"achieves":[137],"greater":[138],"consistency":[139],"individual":[141],"raters,":[142],"improving":[143],"\\approx":[145],"40":[146],"\\%$).":[147],"The":[148],"delivers":[150],"average":[152],"F1-score":[153],"0.84":[155],"across":[156],"validation,":[157],"reducing":[158],"variance":[160],"scalable,":[162],"objective":[163],"assessment.":[164],"aims":[167],"advance":[169],"tool":[171],"support":[172],"automation":[174],"synthesis.":[178]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-03-13T00:00:00"}