Legal Reasoning and EU AI Act Compliance in LIMEN-AI: Auditability through Interpretable Fuzzy Inference Traces

Legal Reasoning and EU AI Act Compliance in LIMEN-AI: Auditability through Interpretable Fuzzy Inference Traces | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Legal Reasoning and EU AI Act Compliance in LIMEN-AI: Auditability through Interpretable Fuzzy Inference Traces Enrico Zanardo This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8462309/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract The rapid ascent of artificial intelligence in the legal domain necessitates architectures that are both performant and compliant with emerging regulatoryframeworks, most notably the European Union Artificial Intelligence Act. This paper presents LIMEN-AI (Lukasiewicz Interpretable Markov Engine for Neuralized AI), a Small Reasoning Model (SRM) engine based on Neuralized Markov Logic Networks, addressing automated legal reasoning and auditability challenges. Unlike Large Language Models operating on parametric patterns,LIMEN-AI focuses on explicit logical grounding through weighted first-order logic with Lukasiewicz fuzzy semantics, where every inference step generates a structured, human-readable trace. We explicitly map the engine’s technical mechanisms—rule weights, ϵ-regularized operators, and energy-based sampling—to the transparency (Article 13), human oversight (Article 14), and accuracy (Article 15) requirements of the AI Act. Through systematic empirical validation, we demonstrate: (1) zero-shot schema adaptation across legal domains, (2) knowledge base evolution through inductive learning (0 to 18 predicates without catastrophic forgetting), (3) document processing scalability (220 words/second on regulatory text), and (4) human override mechanisms with localized intervention effects. Our analysis proposes LIMEN-AI as a compliance-oriented framework designed to facilitate regulatory requirements in high-risk AI systems.The open-source implementation (v0.2.5 on PyPI) enables community validation. While formal user studies and expanded benchmark evaluation remain future work, this validation demonstrates the feasibility of the neuro-symbolic approach for regulatory compliance in legal AI. Legal Reasoning EU AI Act Lukasiewicz logic Explainable AI Neural-symbolic integration Regulatory Compliance Markov Logic Networks Fuzzy Semantics Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8462309","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":567118719,"identity":"fe34a44c-06c3-48d9-805c-38ec71107fbb","order_by":0,"name":"Enrico Zanardo","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABD0lEQVRIiWNgGAWjYJCCA3AWD4MEDxt7A5BlYEG0Fgs5Ph4Q30CCSPt4GCqM5SQSQEzcWvilex8e+FHBYM8/u/nZhzcVEoltks+vbvhRIMHA396dgE2L5JzjBgd7zjAwS9w5ZjxzzhmgFumcsps9QIdJnDm7AZsWgxtpDIcZ2xjYGG4kGDPztoG1pN3gAWoxkMjFqsUeqoVH/kb6Z4gWyTNpN//g0WIgAdEiYXAjB2yLMZsE+7Hb+GyRANoC9IuEgeGNnGJGoF/k2Hhy2G7LGEjw4PIL/4w05g8/Kmzs5W6kb2Z4U1HHI99+/NnNN39s5Pjbe7FqgVmGzOExAJN4lGMA9gekqB4Fo2AUjILhDwBcmFr6Ko3TbAAAAABJRU5ErkJggg==","orcid":"","institution":"Signum Magnum College","correspondingAuthor":true,"prefix":"","firstName":"Enrico","middleName":"","lastName":"Zanardo","suffix":""}],"badges":[],"createdAt":"2025-12-27 16:38:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8462309/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8462309/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106093335,"identity":"9bbc1b31-93e2-475f-88aa-d76a7447c54f","added_by":"auto","created_at":"2026-04-03 11:36:52","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":306211,"visible":true,"origin":"","legend":"","description":"","filename":"p3ezspringerailawhidden.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8462309/v1_covered_5a91565b-af1f-491f-817d-3da75e90f924.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Legal Reasoning and EU AI Act Compliance in LIMEN-AI: Auditability through Interpretable Fuzzy Inference Traces","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Legal Reasoning, EU AI Act, Lukasiewicz logic, Explainable AI, Neural-symbolic integration, Regulatory Compliance, Markov Logic Networks, Fuzzy Semantics","lastPublishedDoi":"10.21203/rs.3.rs-8462309/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8462309/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The rapid ascent of artificial intelligence in the legal domain necessitates architectures that are both performant and compliant with emerging regulatoryframeworks, most notably the European Union Artificial Intelligence Act. This paper presents LIMEN-AI (Lukasiewicz Interpretable Markov Engine for Neuralized AI), a Small Reasoning Model (SRM) engine based on Neuralized Markov Logic Networks, addressing automated legal reasoning and auditability challenges. Unlike Large Language Models operating on parametric patterns,LIMEN-AI focuses on explicit logical grounding through weighted first-order logic with Lukasiewicz fuzzy semantics, where every inference step generates a structured, human-readable trace. We explicitly map the engine’s technical mechanisms—rule weights, ϵ-regularized operators, and energy-based sampling—to the transparency (Article 13), human oversight (Article 14), and accuracy (Article 15) requirements of the AI Act. Through systematic empirical validation, we demonstrate: (1) zero-shot schema adaptation across legal domains, (2) knowledge base evolution through inductive learning (0 to 18 predicates without catastrophic forgetting), (3) document processing scalability (220 words/second on regulatory text), and (4) human override mechanisms with localized intervention effects. Our analysis proposes LIMEN-AI as a compliance-oriented framework designed to facilitate regulatory requirements in high-risk AI systems.The open-source implementation (v0.2.5 on PyPI) enables community validation. While formal user studies and expanded benchmark evaluation remain future work, this validation demonstrates the feasibility of the neuro-symbolic approach for regulatory compliance in legal AI.","manuscriptTitle":"Legal Reasoning and EU AI Act Compliance in LIMEN-AI: Auditability through Interpretable Fuzzy Inference Traces","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-28 09:37:57","doi":"10.21203/rs.3.rs-8462309/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"f9898b76-5e6a-4bb8-aef9-2f3d8dabedef","owner":[],"postedDate":"January 28th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-01T22:09:03+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-28 09:37:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8462309","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8462309","identity":"rs-8462309","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}