Bridging Legal Interpretation and Formal Logic: Faithfulness, Assumption, and the Future of AI Legal Reasoning

TL;DR

This paper proposes a neuro-symbolic approach combining large language models with formal verification to improve the trustworthiness and rigor of AI legal reasoning.

Contribution

It introduces a novel neuro-symbolic framework that enhances legal AI's reasoning capabilities while ensuring accountability and reducing manual verification.

Findings

Demonstrates improved logical consistency in legal AI reasoning

Reduces hallucinations and unsupported inferences in LLMs

Enhances trustworthiness of AI in high-stakes legal tasks

Abstract

The growing adoption of large language models in legal practice brings both significant promise and serious risk. Legal professionals stand to benefit from AI that can reason over contracts, draft documents, and analyze sources at scale, yet the high-stakes nature of legal work demands a level of rigor that current AI systems do not provide. The central problem is not simply that LLMs hallucinate facts and references; it is that they systematically draw inferences that go beyond what the source text actually supports, presenting assumption-laden conclusions as if they were logically grounded. 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, aiming to make AI-assisted legal reasoning both capable and trustworthy, thus reducing the burden of manual verification without sacrificing the accountability that legal practice demands.