Closing the Loop: Formally Verified Law as a Reward Signal for Self-Improving Legal AI

• URL: http://arxiv.org/abs/2606.23913v1
• Date: Mon, 22 Jun 2026 20:21:49 GMT
• Title: Closing the Loop: Formally Verified Law as a Reward Signal for Self-Improving Legal AI
• Abstract summary: This article develops an architecture that creates a formally verifiable reward signal to train legal AI.<n>For the computational components of law, the architecture provides provable correctness.<n>We show that the same architecture has a structural advantage for legal AI training.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This article develops an architecture that creates a formally verifiable reward signal to train legal AI, adapting the LLM proposes, verifier disposes paradigm from mathematical AI to the distinctive demands of law. We present an architecture comprising LLM-driven autoformalization into a formal legal calculus extending Catala, a verification kernel, and explanation generation grounded in formal proof traces. For the computational components of law, the architecture provides provable correctness. For open-textured legal analysis, it provides structural guarantees: every required stage of the legal argument is addressed, argumentation is exercised at the correct stages and not omitted, and the deductive links between steps are valid. We demonstrate the architecture on procedural deadline calculations in German law, Commerce Clause analysis in U.S. constitutional law, and cross-jurisdictional sanction proportionality. We further show that the same architecture has a structural advantage for legal AI training: a deterministic external verifier supplies verifiable outcomes for legal problems and thereby closes the traditional reinforcement-learning loop gap in law.

Related papers

• Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering [54.97384993676565]
  We formalize Regulatory Compliance QA with RegOps-Bench, a novel benchmark featuring an Operational Knowledge Graph derived from complex national R&D regulations.<n>RefWalk traverses cross-document citations, fuses multi-view candidates via max-based aggregation, and enforces per-rule attribution to explicitly map claims to sources.
  arXiv  Detail & Related papers  (2026-05-28T10:38:38Z)
• Bridging Legal Interpretation and Formal Logic: Faithfulness, Assumption, and the Future of AI Legal Reasoning [3.093890460224435]
  The growing adoption of large language models in legal practice brings both significant promise and serious risk.<n>This proposal presents a neuro-symbolic approach to legal AI that combines the expressive power of large language models with the rigor of formal verification.
  arXiv  Detail & Related papers  (2026-05-13T19:11:09Z)
• Legal2LogicICL: Improving Generalization in Transforming Legal Cases to Logical Formulas via Diverse Few-Shot Learning [1.315248337031741]
  This work aims to improve the generalization of logic-based legal reasoning systems by integrating recent advances in NLP with legal-domain adaptive few-shot learning techniques using LLMs.<n>We introduce Legal2LogicICL, a few-shot retrieval framework that balances diversity and similarity of exemplars at both the latent semantic representation level and the legal text structure level.<n>Our approach significantly improves accuracy, stability, and generalization in transforming natural-language legal case descriptions into logical representations.
  arXiv  Detail & Related papers  (2026-04-13T16:36:48Z)
• Compliance-by-Construction Argument Graphs: Using Generative AI to Produce Evidence-Linked Formal Arguments for Certification-Grade Accountability [0.0]
  This paper proposes a compliance-by-construction architecture that integrates Generative AI (GenAI) with structured formal argument representations.<n>The architecture treats each AI-assisted step as a claim that must be supported by verifiable evidence and validated against explicit reasoning constraints.<n>The analysis suggests that validation rules can prevent unsupported claims from entering the decision record while allowing GenAI to accelerate argument construction.
  arXiv  Detail & Related papers  (2026-04-05T12:55:16Z)
• LawThinker: A Deep Research Legal Agent in Dynamic Environments [51.782293183431676]
  LawThinker is an autonomous legal research agent.<n>It enforces verification as an atomic operation after every knowledge exploration step.<n>LawThinker achieves a 24% improvement over direct reasoning.
  arXiv  Detail & Related papers  (2026-02-12T15:19:11Z)
• LegalOne: A Family of Foundation Models for Reliable Legal Reasoning [54.57434222018289]
  We present LegalOne, a family of foundational models specifically tailored for the Chinese legal domain.<n>LegalOne is developed through a comprehensive three-phase pipeline designed to master legal reasoning.<n>We publicly release the LegalOne weights and the LegalKit evaluation framework to advance the field of Legal AI.
  arXiv  Detail & Related papers  (2026-01-31T10:18:32Z)
• On Verifiable Legal Reasoning: A Multi-Agent Framework with Formalized Knowledge Representations [0.0]
  This paper introduces a modular multi-agent framework that decomposes legal reasoning into distinct knowledge acquisition and application stages.<n>In the first stage, specialized agents extract legal concepts and formalize rules to create verifiable intermediate representations of statutes.<n>The second stage applies this knowledge to specific cases through three steps: analyzing queries to map case facts onto the schema, performing symbolic inference to derive logically entailed conclusions, and generating final answers.
  arXiv  Detail & Related papers  (2025-08-31T06:03:00Z)
• GLARE: Agentic Reasoning for Legal Judgment Prediction [60.13483016810707]
  Legal judgment prediction (LJP) has become increasingly important in the legal field.<n>Existing large language models (LLMs) have significant problems of insufficient reasoning due to a lack of legal knowledge.<n>We introduce GLARE, an agentic legal reasoning framework that dynamically acquires key legal knowledge by invoking different modules.
  arXiv  Detail & Related papers  (2025-08-22T13:38:12Z)
• RLJP: Legal Judgment Prediction via First-Order Logic Rule-enhanced with Large Language Models [58.69183479148083]
  Legal Judgment Prediction (LJP) is a pivotal task in legal AI.<n>Existing LJP models integrate judicial precedents and legal knowledge for high performance.<n>But they neglect legal reasoning logic, a critical component of legal judgments requiring rigorous logical analysis.<n>This paper proposes a rule-enhanced legal judgment prediction framework based on first-order logic (FOL) formalism and comparative learning (CL)
  arXiv  Detail & Related papers  (2025-05-27T14:50:21Z)
• DELTA: Pre-train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment [55.91429725404988]
  We introduce DELTA, a discriminative model designed for legal case retrieval. We leverage shallow decoders to create information bottlenecks, aiming to enhance the representation ability. Our approach can outperform existing state-of-the-art methods in legal case retrieval.
  arXiv  Detail & Related papers  (2024-03-27T10:40:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.