autoformalize legal text

To address challenges in legal compliance checking—including high subjectivity in regulatory interpretation, dynamic evolution of legislation, and difficulties in cross-disciplinary collaboration—this paper introduces eFLINT, a domain-specific language for computable modeling and automated verification of legal rules, regulatory requirements, and contractual clauses. eFLINT integrates declarative and procedural paradigms, explicitly linking legal concepts to executable computational logic. It combines formal specification, context-aware reasoning, and scenario-based modeling to enable dynamic, end-to-end compliance verification across system design, runtime, and post-execution phases. Designed to balance expressiveness and executability, eFLINT reconciles conflicting requirements through principled language design. Drawing on multi-scenario industrial deployments, the paper distills actionable design principles and a methodology for automation-oriented compliance languages. It contributes both a reusable technical framework and theoretical foundations for computable regulation research in legal technology.

This work addresses the error-prone and labor-intensive process of manually translating regulatory texts such as the GDPR and the EU AI Act into actionable software requirements. The authors propose Reg2Req, the first end-to-end automated pipeline that leverages natural language processing to identify regulatory provisions, generate system-agnostic software requirements accompanied by plain-language explanations, and establish traceability links. The approach supports requirement classification, use case seed generation, and cross-reference analysis, achieving macro-averaged F1 scores of 0.82 on the GDPR and 0.78 on the EU AI Act. A user study demonstrates that the generated plain-language explanations significantly enhance users’ comprehension and confidence in taking compliance actions (p < 0.001), with all participants expressing willingness to adopt the output as a starting point for compliance efforts.

Normative requirements—encompassing Social, Legal, Ethical, Empathic, and Cultural (SLEEC) dimensions—are notoriously difficult to comprehend, debug, and verify in multi-stakeholder collaborative settings due to their inherent ambiguity and non-technical nature. Method: This paper introduces SLEEC-LLM, the first framework to leverage large language models (LLMs) for generating natural-language explanations of counterexamples revealing SLEEC requirement inconsistencies—thereby bridging the cognitive gap between formal verification outputs and non-technical stakeholders. It integrates a domain-specific language (DSL), model checking, and LLM-based explanation generation to produce human-readable, semantically precise interpretations. Results: Evaluated on two real-world case studies, SLEEC-LLM significantly improves non-technical stakeholders’ comprehension speed (62% reduction in time-to-understanding) and conflict identification accuracy (+38%). It markedly reduces cognitive load during requirement iteration and advances explainable, collaborative requirements engineering.

To address the inefficiency and error-proneness of manual regulatory compliance checking, this paper proposes an OWL DL formalization method for natural language specifications. The method introduces a novel structured text annotation scheme and employs a rule-driven deterministic transformation algorithm to automatically map specification texts to OWL DL ontologies. It further integrates Protégé with the HermiT reasoner to enable machine-readable semantic representation and automated compliance verification. A proof-of-concept evaluation in the construction domain demonstrates successful translation of multiple natural language regulations into OWL DL ontologies and accurate identification of compliant and non-compliant scenarios. This work bridges a critical gap between regulatory semantic modeling and automated reasoning, delivering a scalable, methodology-driven foundation for automating compliance checking.

This work addresses the inefficiency and high cost of compliance testing in highly regulated domains, where current practices rely on manual translation of regulations into test cases by experts. While large language models (LLMs) offer automation potential, they often suffer from hallucination, and existing hybrid approaches still require significant human modeling effort. To overcome these limitations, the authors propose RAFT, a novel framework that explicitly extracts implicit regulatory knowledge from multiple LLMs and leverages an adaptive purification-aggregation strategy with dynamic prompt injection to automatically generate domain-specific meta-models, formalized requirements, and testability constraints—enabling fully automated, human-intervention-free compliance test generation. Experiments in financial, automotive, and power sectors demonstrate that RAFT achieves expert-level performance, significantly outperforming state-of-the-art methods while drastically reducing test case generation and review time.

This work addresses the challenge of ensuring program correctness in natural language-to-code generation, which is often hindered by the absence of high-quality formal specifications. The authors propose VeriSpecGen, a framework that decomposes natural language requirements into atomic clauses through a traceable refinement mechanism, generates requirement-driven tests with explicit traceability mappings, and synthesizes formal specifications aligned with user intent by localizing and repairing faulty clauses upon verification failure. Integrating large language models (e.g., Claude Opus 4.5) with the Lean proof assistant, the approach leverages refinement trajectories to generate 343K training samples, substantially enhancing model generalization and reasoning capabilities. Evaluated on the VERINA SpecGen benchmark, VeriSpecGen achieves an accuracy of 86.6%, outperforming the best baseline by up to 31.8 percentage points and demonstrating a relative improvement of 62–106% in specification synthesis performance.

Modern slavery compliance auditing faces challenges including ambiguous corporate disclosures, inefficient and non-scalable manual assessments, and a lack of legal verifiability. Existing AI approaches typically reduce compliance evaluation to binary classification, neglecting rule-level traceability and statutory grounding. This paper proposes a rule-aligned AI framework comprising two components: (1) CA-Judge, a compliance-aligned discriminative model, and (2) CALLM, a compliance-oriented large language model. The framework formalizes compliance verification as a fine-grained rule-matching task, integrating statutory requirement-driven feedback, NLP-based analysis, and explainability techniques. Empirical results show that CALLM significantly outperforms baselines in prediction accuracy, output transparency, and legal grounding—generating auditable, traceable, and regulation-aligned conclusions. To our knowledge, this is the first framework enabling automated, structured, and expert-controllable modern slavery statement assessment, thereby enhancing regulatory efficiency and judicial trustworthiness.

This work addresses the growing complexity of financial regulations, which hinders the automation of logically consistent and low-intervention compliance processes. The authors propose a neuro-symbolic compliance framework that integrates large language models (LLMs) with SMT solvers: the LLM translates regulatory texts and enforcement cases into formal constraints, while the SMT solver verifies their logical consistency and computes minimal factual modifications to automatically rectify violations. Centered on logic-driven optimization, the approach prioritizes verifiable legal consistency reasoning over post-hoc interpretability. Evaluated on 87 enforcement cases from Taiwan’s Financial Supervisory Commission, the method achieves an 86.2% accuracy in SMT constraint generation, improves reasoning efficiency by over 100-fold, and effectively sustains corrective actions for regulatory violations.

This work addresses the challenge of automatically generating semantic-aligned and verifiable formal properties from unstructured natural language requirements. The authors propose a novel large language model (LLM)-based agent architecture that, for the first time, explicitly integrates modeling and verification constraints into the requirement formalization pipeline. Through a modular design, the approach unifies requirement extraction, formalization compatibility filtering, and property translation into a cohesive workflow. Evaluated across three real-world scenarios, the method achieves an accuracy of 77.8%, substantially improving the syntactic correctness, semantic alignment, and verifiability of the generated formal properties.

This study addresses the high complexity and labor-intensive challenges of accurately translating privacy regulations such as Brazil’s General Data Protection Law (LGPD) into actionable software requirements. It presents the first systematic exploration of leveraging large language models (LLMs) for generating LGPD-compliant requirements, proposing an automated approach that integrates legal text analysis with requirements engineering to directly map statutory provisions into user stories and acceptance test scenarios. Experimental results demonstrate that the method efficiently produces high-quality, executable compliance requirements, significantly supporting regulatory adherence during early-stage software development. This work thus offers an innovative and practical technical pathway for privacy regulation–driven requirements engineering.