{"id":"https://openalex.org/W7161536769","doi":"https://doi.org/10.48550/arxiv.2605.16198","title":"Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems","display_name":"Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161536769","doi":"https://doi.org/10.48550/arxiv.2605.16198"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.16198","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16198","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.16198","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114640431","display_name":"Parand A. Alamdari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alamdari, Parand A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136410642","display_name":"Toryn Q. Klassen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Klassen, Toryn Q.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041982650","display_name":"Sheila A. McIlraith","orcid":"https://orcid.org/0000-0003-4953-0945"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"McIlraith, Sheila A.","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.27570000290870667,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.27570000290870667,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.20350000262260437,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.13459999859333038,"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/audit","display_name":"Audit","score":0.616599977016449},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4952999949455261},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48080000281333923},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.47200000286102295},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4187000095844269},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.4097999930381775},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.4043999910354614},{"id":"https://openalex.org/keywords/linear-temporal-logic","display_name":"Linear temporal logic","score":0.3871999979019165},{"id":"https://openalex.org/keywords/intervention","display_name":"Intervention (counseling)","score":0.3831999897956848}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663000226020813},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.616599977016449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.538100004196167},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4952999949455261},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.47200000286102295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4657000005245209},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.41449999809265137},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.4043999910354614},{"id":"https://openalex.org/C4777664","wikidata":"https://www.wikidata.org/wiki/Q1536492","display_name":"Linear temporal logic","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C75606506","wikidata":"https://www.wikidata.org/wiki/Q1049183","display_name":"Formal methods","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C2781460075","wikidata":"https://www.wikidata.org/wiki/Q1399332","display_name":"Compliance (psychology)","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C116253237","wikidata":"https://www.wikidata.org/wiki/Q1437424","display_name":"Formal specification","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3093999922275543},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C2989277270","wikidata":"https://www.wikidata.org/wiki/Q168338","display_name":"Behavioral analysis","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2529999911785126},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.16198","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16198","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.16198","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16198","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,87,181],"examine":[1],"one":[2],"particular":[3],"dimension":[4],"of":[5,64,126,146,173,202,206],"AI":[6,19,52,83],"governance:":[7],"how":[8],"to":[9,25,56,80,108,139],"monitor":[10],"and":[11,15,44,54,60,76,99,110,124,134,165,204],"audit":[12],"AI-enabled":[13,42],"products":[14],"services":[16],"throughout":[17],"the":[18,121,170],"development":[20],"lifecycle,":[21],"from":[22,30],"pre-deployment":[23],"testing":[24],"post-deployment":[26],"auditing.":[27],"Combining":[28],"principles":[29],"formal":[31,122],"methods":[32,142],"with":[33,78,151,197],"SoTA":[34],"machine":[35],"learning,":[36],"we":[37,100],"propose":[38],"techniques":[39,91,136],"that":[40,104,118,187],"enable":[41],"product":[43],"service":[45],"developers,":[46],"as":[47,49,71,96],"well":[48],"third":[50],"party":[51],"developers":[53],"evaluators,":[55],"perform":[57],"offline":[58],"auditing":[59,133],"online":[61],"(runtime)":[62],"monitoring":[63,135],"product-specific":[65],"(temporally":[66],"extended)":[67],"behavioral":[68,149],"constraints":[69],"such":[70,95],"safety":[72],"constraints,":[73,203],"norms,":[74],"rules":[75],"regulations":[77],"respect":[79],"black-box":[81],"advanced":[82],"systems,":[84],"notably":[85],"LLMs.":[86],"further":[88,182],"provide":[89],"practical":[90],"for":[92],"predictive":[93,164],"monitoring,":[94],"sampling-based":[97],"methods,":[98],"introduce":[101],"intervening":[102,166],"monitors":[103,167],"act":[105],"at":[106],"runtime":[107],"preempt":[109],"potentially":[111],"mitigate":[112],"predicted":[113],"violations.":[114],"Experimental":[115],"results":[116],"show":[117,183],"by":[119],"exploiting":[120],"syntax":[123],"semantics":[125],"Linear":[127],"Temporal":[128],"Logic":[129],"(LTL),":[130],"our":[131,152],"proposed":[132],"are":[137],"superior":[138],"LLM":[140,161],"baseline":[141],"in":[143,195],"detecting":[144],"violations":[145],"temporally":[147],"extended":[148],"constraints;":[150],"approach,":[153],"even":[154],"small-model":[155],"labelers":[156],"match":[157],"or":[158],"exceed":[159],"frontier":[160],"judges.":[162],"Our":[163],"significantly":[168],"reduce":[169],"violation":[171],"rates":[172],"LLM-based":[174],"agents":[175],"while":[176],"largely":[177],"preserving":[178],"task":[179],"performance.":[180],"through":[184],"controlled":[185],"experiments":[186],"LLMs'":[188],"temporal":[189],"reasoning":[190],"shows":[191],"a":[192],"pronounced":[193],"degradation":[194],"accuracy":[196],"increasing":[198],"event":[199],"distance,":[200],"number":[201,205],"propositions.":[207]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-19T00:00:00"}