mlsanityData to 7 Oct 2026

Towards Robust Legal Reasoning: Harnessing Logical LLMs in Law

arXiv 2502.17638 ↗First posted 24 Feb 2025cs.CY cs.AIcited by 30

On the map: LLM reasoning → Reasoning for agents, planning and code

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.

Key facts. Cited by 30 papers in the map (data through 7 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.

Builds on

10 of 27 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models20 Aug

Other references · 9

  1. 2024Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Toolscited by 170
  2. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approachescited by 43
  3. 2025Neuro-Symbolic AI in 2024: A Systematic Reviewcited by 36
  4. 2024Logically Consistent Language Models via Neuro-Symbolic Integrationcited by 30
  5. 2025Fine-tuning Large Language Models for Improving Factuality in Legal Question Answeringcited by 28
  6. 2025LLMs Provide Unstable Answers to Legal Questionscited by 19
  7. 2019Integrating Deep Learning with Logic Fusion for Information Extractioncited by 15
  8. 2024Logic Rules as Explanations for Legal Case Retrievalcited by 5
  9. 2025Artificial Intelligence and Legal Analysis: Implications for Legal Education and the Professioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 13; 2026: 17.

30 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  2. 2025On Verifiable Legal Reasoning: A Multi-Agent Framework with Formalized Knowledge Representationscited by 16
  3. 2025Explainable Rule Application via Structured Prompting: A Neural-Symbolic Approachcited by 14
  4. 2025Challenges for Generative AI in Legal Reasoningcited by 7
  5. 2026Quantum-Audit: Evaluating the Reasoning Limits of LLMs on Quantum Computingcited by 5
  6. 2025Compliance-to-Code: Enhancing Financial Compliance Checking via Code Generationcited by 4
  7. 2025Language Models and Logic Programs for Trustworthy Tax Reasoningcited by 4
  8. 2025Towards Trustworthy Legal AI through LLM Agents and Formal Reasoningcited by 4
  9. 2025Bye-bye, Bluebook? Automating Legal Drudgery With AI-Augmented Rule Followingcited by 3
  10. 2025LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligencecited by 3
  11. 2026Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoningcited by 3
  12. 2025PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreementscited by 1
18 more
  1. 2025Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processescited by 1
  2. 2025CLaw: Benchmarking Chinese Legal Knowledge in Large Language Models - A Fine-grained Corpus and Reasoning Analysiscited by 1
  3. 2026Structured Decomposition for LLM Reasoning: Cross-Domain Validation and Semantic Web Integrationcited by 1
  4. 2026Autonomous Business System via Neuro-symbolic AIcited by 1
  5. 2026Beyond Imperfect Alternatives with Rulemapping: A Neuro-Symbolic Case Study on Online Hate Speechcited by 1
  6. 2025LLM-Assisted Formalization Enables Deterministic Detection of Statutory Inconsistency in the Internal Revenue Codecited by 0
  7. 2026From Policy to Logic for Efficient and Interpretable Coverage Assessmentcited by 0
  8. 2026ART: Adaptive Reasoning Trees for Explainable Claim Verificationcited by 0
  9. 2026LAMUS: A Large-Scale Corpus for Legal Argument Mining from U.S. Caselaw using LLMscited by 0
  10. 2026Human Attribution of Causality to AI Across Agency, Misuse, and Misalignmentcited by 0
  11. 2026GDPR Auto-Formalization with AI Agents and Human Verificationcited by 0
  12. 2026Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudicationcited by 0
  13. 2026Which Changes Matter? Towards Trustworthy Legal AI via Relevance-Sensitive Evaluation and Solver-Grounded Reasoningcited by 0
  14. 2026Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branchescited by 0
  15. 2026Abliteration Mitigation via Refusal Aliasescited by 0
  16. 2026Solving versus Verifying: Catching Contradictions in Tax Reasoning Systemscited by 0
  17. 2026Code-as-Auditor: Executable Compliance Reasoning via Regulation-to-Codecited by 0
  18. 2026From Alignment to Access Control: A Framework for GenAI Policy Enforcementcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Bridging Legal Interpretation and Formal Logic: Faithfulness, Assumption, and the Future of AI Legal Reasoning
  2. 2024Equitable Access to Justice: Logical LLMs Show Promise
  3. 2026NeuroSymbolic AI for Legal AI-TRISM: Trustworthy, Reliable, Interpretable, Safe Models
  4. 2025Better Call CLAUSE: A Discrepancy Benchmark for Auditing LLMs Legal Reasoning Capabilities
  5. 2023Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergence
  6. 2026Reasoners or Translators? Contamination-aware Evaluation and Neuro-Symbolic Robustness in Tax Law
  7. 2025Logical Lease Litigation: Prolog and LLMs for Rental Law Compliance in New York
  8. 2025LOGicalThought: Logic-Based Ontological Grounding of LLMs for High-Assurance Reasoning