# Towards Robust Legal Reasoning: Harnessing Logical LLMs in Law

arXiv: https://arxiv.org/abs/2502.17638 · HTML: https://mlsanity.com/paper/2502.17638/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 10 of its 27 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 10 of 10)

- [LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models](https://mlsanity.com/paper/2308.11462/) (2023)
- [Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools](https://mlsanity.com/paper/2405.20362/) (2024)
- [Advancing Reasoning in Large Language Models: Promising Methods and Approaches](https://mlsanity.com/paper/2502.03671/) (2025)
- [Neuro-Symbolic AI in 2024: A Systematic Review](https://mlsanity.com/paper/2501.05435/) (2025)
- [Logically Consistent Language Models via Neuro-Symbolic Integration](https://mlsanity.com/paper/2409.13724/) (2024)
- [Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering](https://mlsanity.com/paper/2501.06521/) (2025)
- [LLMs Provide Unstable Answers to Legal Questions](https://mlsanity.com/paper/2502.05196/) (2025)
- [Integrating Deep Learning with Logic Fusion for Information Extraction](https://mlsanity.com/paper/1912.03041/) (2019)
- [Logic Rules as Explanations for Legal Case Retrieval](https://mlsanity.com/paper/2403.01457/) (2024)
- [Artificial Intelligence and Legal Analysis: Implications for Legal Education and the Profession](https://mlsanity.com/paper/2502.03487/) (2025)

## Built on by (most cited first, 30 of 30)

- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [On Verifiable Legal Reasoning: A Multi-Agent Framework with Formalized Knowledge Representations](https://mlsanity.com/paper/2509.00710/) (2025)
- [Explainable Rule Application via Structured Prompting: A Neural-Symbolic Approach](https://mlsanity.com/paper/2506.16335/) (2025)
- [Challenges for Generative AI in Legal Reasoning](https://mlsanity.com/paper/2508.18880/) (2025)
- [Towards Trustworthy Legal AI through LLM Agents and Formal Reasoning](https://mlsanity.com/paper/2511.21033/) (2025)
- [Quantum-Audit: Evaluating the Reasoning Limits of LLMs on Quantum Computing](https://mlsanity.com/paper/2602.10092/) (2026)
- [Compliance-to-Code: Enhancing Financial Compliance Checking via Code Generation](https://mlsanity.com/paper/2505.19804/) (2025)
- [Language Models and Logic Programs for Trustworthy Tax Reasoning](https://mlsanity.com/paper/2508.21051/) (2025)
- [LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence](https://mlsanity.com/paper/2512.04578/) (2025)
- [Bye-bye, Bluebook? Automating Legal Drudgery With AI-Augmented Rule Following](https://mlsanity.com/paper/2505.02763/) (2025)
- [Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning](https://mlsanity.com/paper/2606.16118/) (2026)
- [PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreements](https://mlsanity.com/paper/2506.00608/) (2025)
- [Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes](https://mlsanity.com/paper/2507.22940/) (2025)
- [CLaw: Benchmarking Chinese Legal Knowledge in Large Language Models - A Fine-grained Corpus and Reasoning Analysis](https://mlsanity.com/paper/2509.21208/) (2025)
- [Structured Decomposition for LLM Reasoning: Cross-Domain Validation and Semantic Web Integration](https://mlsanity.com/paper/2601.01609/) (2026)
- [Autonomous Business System via Neuro-symbolic AI](https://mlsanity.com/paper/2601.15599/) (2026)
- [Beyond Imperfect Alternatives with Rulemapping: A Neuro-Symbolic Case Study on Online Hate Speech](https://mlsanity.com/paper/2605.16280/) (2026)
- [Code-as-Auditor: Executable Compliance Reasoning via Regulation-to-Code](https://mlsanity.com/paper/2609.19199/) (2026)
- [LLM-Assisted Formalization Enables Deterministic Detection of Statutory Inconsistency in the Internal Revenue Code](https://mlsanity.com/paper/2511.11954/) (2025)
- [From Policy to Logic for Efficient and Interpretable Coverage Assessment](https://mlsanity.com/paper/2601.01266/) (2026)
- [ART: Adaptive Reasoning Trees for Explainable Claim Verification](https://mlsanity.com/paper/2601.05455/) (2026)
- [LAMUS: A Large-Scale Corpus for Legal Argument Mining from U.S. Caselaw using LLMs](https://mlsanity.com/paper/2603.08286/) (2026)
- [Human Attribution of Causality to AI Across Agency, Misuse, and Misalignment](https://mlsanity.com/paper/2603.13236/) (2026)
- [GDPR Auto-Formalization with AI Agents and Human Verification](https://mlsanity.com/paper/2604.14607/) (2026)
- [Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudication](https://mlsanity.com/paper/2605.02472/) (2026)
- [Which Changes Matter? Towards Trustworthy Legal AI via Relevance-Sensitive Evaluation and Solver-Grounded Reasoning](https://mlsanity.com/paper/2605.26530/) (2026)
- [Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches](https://mlsanity.com/paper/2606.01145/) (2026)
- [Abliteration Mitigation via Refusal Aliases](https://mlsanity.com/paper/2608.18093/) (2026)
- [Solving versus Verifying: Catching Contradictions in Tax Reasoning Systems](https://mlsanity.com/paper/2609.05928/) (2026)
- [From Alignment to Access Control: A Framework for GenAI Policy Enforcement](https://mlsanity.com/paper/2609.26682/) (2026)

## Abstract (arXiv)

Legal services rely heavily on text processing. While large language models (LLMs) show promise, their application in legal contexts demands higher accuracy, repeatability, and transparency. Logic programs, by encoding legal concepts as structured rules and facts, offer reliable automation, but require sophisticated text extraction. We propose a neuro-symbolic approach that integrates LLMs' natural language understanding with logic-based reasoning to address these limitations. As a legal document case study, we applied neuro-symbolic AI to coverage-related queries in insurance contracts using both closed and open-source LLMs. While LLMs have improved in legal reasoning, they still lack the accuracy and consistency required for complex contract analysis. In our analysis, we tested three methodologies to evaluate whether a specific claim is covered under a contract: a vanilla LLM, an unguided approach that leverages LLMs to encode both the contract and the claim, and a guided approach that uses a framework for the LLM to encode the contract. We demonstrated the promising capabilities of LLM + Logic in the guided approach.