{"id":"https://openalex.org/W7160830587","doi":"https://doi.org/10.1007/s10994-026-07038-6","title":"LLM-Driven Compliance Checking for Natural-Language Policies over Data Product Descriptors","display_name":"LLM-Driven Compliance Checking for Natural-Language Policies over Data Product Descriptors","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7160830587","doi":"https://doi.org/10.1007/s10994-026-07038-6"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-026-07038-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-026-07038-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-026-07038-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-026-07038-6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135880262","display_name":"Francesco Simbola","orcid":null},"institutions":[{"id":"https://openalex.org/I172446870","display_name":"University of Cagliari","ror":"https://ror.org/003109y17","country_code":"IT","type":"education","lineage":["https://openalex.org/I172446870"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Simbola","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, 09124, Cagliari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, 09124, Cagliari, Italy","institution_ids":["https://openalex.org/I172446870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014673075","display_name":"Diego Reforgiato Recupero","orcid":"https://orcid.org/0000-0001-8646-6183"},"institutions":[{"id":"https://openalex.org/I172446870","display_name":"University of Cagliari","ror":"https://ror.org/003109y17","country_code":"IT","type":"education","lineage":["https://openalex.org/I172446870"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Diego Reforgiato Recupero","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, 09124, Cagliari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, 09124, Cagliari, Italy","institution_ids":["https://openalex.org/I172446870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074097123","display_name":"Daniele Riboni","orcid":"https://orcid.org/0000-0002-0695-2040"},"institutions":[{"id":"https://openalex.org/I172446870","display_name":"University of Cagliari","ror":"https://ror.org/003109y17","country_code":"IT","type":"education","lineage":["https://openalex.org/I172446870"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Daniele Riboni","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, 09124, Cagliari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, 09124, Cagliari, Italy","institution_ids":["https://openalex.org/I172446870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135853619","display_name":"Martina Salis","orcid":null},"institutions":[{"id":"https://openalex.org/I172446870","display_name":"University of Cagliari","ror":"https://ror.org/003109y17","country_code":"IT","type":"education","lineage":["https://openalex.org/I172446870"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Martina Salis","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, 09124, Cagliari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, 09124, Cagliari, Italy","institution_ids":["https://openalex.org/I172446870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5014673075"],"corresponding_institution_ids":["https://openalex.org/I172446870"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5651865,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"115","issue":"5","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.6947000026702881,"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"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.6947000026702881,"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"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.06030000001192093,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.05920000001788139,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6516000032424927},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6425999999046326},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5378999710083008},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4494999945163727},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.3935999870300293},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.37139999866485596},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.32339999079704285},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.30379998683929443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504000067710876},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6516000032424927},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6425999999046326},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5378999710083008},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45339998602867126},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.439300000667572},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41679999232292175},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.32339999079704285},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2662000060081482},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C2781460075","wikidata":"https://www.wikidata.org/wiki/Q1399332","display_name":"Compliance (psychology)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-026-07038-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-026-07038-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-026-07038-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-026-07038-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-026-07038-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-026-07038-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4831975996494293,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313987","display_name":"Universit\u00e0 degli Studi di Cagliari","ror":"https://ror.org/003109y17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160830587.pdf","grobid_xml":"https://content.openalex.org/works/W7160830587.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1535992660","https://openalex.org/W2046608357","https://openalex.org/W2060964996","https://openalex.org/W2091359547","https://openalex.org/W2183400721","https://openalex.org/W2602686199","https://openalex.org/W2765612995","https://openalex.org/W3036911563","https://openalex.org/W3215681274","https://openalex.org/W4285305524","https://openalex.org/W4310529830","https://openalex.org/W4385571243","https://openalex.org/W4388962452","https://openalex.org/W4389519543","https://openalex.org/W4400209938","https://openalex.org/W4403661543","https://openalex.org/W4403963503","https://openalex.org/W4405055939","https://openalex.org/W4406321864","https://openalex.org/W4408960620","https://openalex.org/W4412779834","https://openalex.org/W7107871452"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Modern":[1],"data":[2,8,68],"architectures":[3],"increasingly":[4],"rely":[5],"on":[6],"decentralized":[7],"products":[9],"described":[10],"through":[11],"semi-structured":[12,67,182],"artifacts,":[13],"such":[14],"as":[15,79,88,198,200,230],"YAML":[16],"descriptors,":[17],"to":[18,42,62,108,137,141,186],"support":[19,109,178],"scalability,":[20],"interoperability,":[21],"and":[22,31,37,48,93,144,158,168,208,218,225],"governance.":[23],"Ensuring":[24],"that":[25,99,174,227],"these":[26],"descriptors":[27,70],"comply":[28],"with":[29,104],"organizational":[30],"regulatory":[32],"policies":[33,47,65,229],"remains":[34],"a":[35,59,89,192],"challenging":[36],"labor-intensive":[38],"task,":[39],"largely":[40],"due":[41],"the":[43,49,84,115,216,219],"natural-language":[44,64],"nature":[45],"of":[46,51,163,222],"heterogeneity":[50],"descriptor":[52,147],"schemas.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,117,190],"investigate":[58],"model-based":[60],"approach":[61],"evaluating":[63],"over":[66],"product":[69],"expressed":[71],"in":[72,161,181],"YAML,":[73],"leveraging":[74],"Large":[75],"Language":[76],"Models":[77],"(LLMs)":[78],"reasoning":[80],"components.":[81],"We":[82,149],"formalize":[83],"policy-descriptor":[85,124],"compliance":[86],"task":[87],"binary":[90],"decision":[91],"problem":[92],"propose":[94],"an":[95,119],"LLM-based":[96],"microservice":[97],"architecture":[98],"combines":[100],"structured":[101],"prompt":[102],"engineering":[103],"deterministic":[105],"output":[106],"constraints":[107],"automated":[110],"policy":[111,142,179],"verification.":[112],"To":[113],"evaluate":[114,150],"approach,":[116],"construct":[118],"augmentation-based":[120],"benchmark":[121,134],"comprising":[122],"4,000":[123],"pairs":[125],"derived":[126],"from":[127],"40":[128],"manually":[129],"annotated":[130],"seed":[131],"combinations.":[132],"The":[133],"is":[135],"designed":[136],"assess":[138],"model":[139],"robustness":[140],"paraphrases":[143],"semantically":[145],"equivalent":[146],"rewrites.":[148],"four":[151],"open-source":[152],"instruction-tuned":[153],"LLMs":[154,175],"under":[155],"identical":[156],"conditions":[157],"report":[159],"results":[160,172],"terms":[162],"accuracy,":[164],"precision,":[165],"recall,":[166],"F1-score,":[167],"execution":[169],"time.":[170],"Experimental":[171],"show":[173],"can":[176],"effectively":[177],"verification":[180],"environments,":[183],"achieving":[184],"up":[185],"72%":[187],"accuracy.":[188],"However,":[189],"observe":[191],"consistent":[193],"conservative":[194],"bias":[195],"toward":[196],"non-compliance,":[197],"well":[199],"systematic":[201],"failure":[202],"modes":[203],"involving":[204],"conjunctions,":[205],"bidirectional":[206],"constraints,":[207],"conditionally":[209],"inapplicable":[210],"rules.":[211],"Our":[212],"analysis":[213],"highlights":[214],"both":[215],"potential":[217],"current":[220],"limitations":[221],"LLM-driven":[223],"governance,":[224],"suggests":[226],"expressing":[228],"explicit":[231],"procedural":[232],"checks":[233],"substantially":[234],"improves":[235],"validation":[236],"reliability.":[237]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-05-12T00:00:00"}