Trustworthy Legal Reasoning: A Comprehensive Survey
Preprint
- 12 February 2026
- preprint
- Published by MDPI AG in Preprints.org
Abstract
As large language models are increasingly used for contract drafting, case research and even judicial work, a central question is how to make their outputs trustworthy. This survey addresses that question through the lens of verified generation for legal AI, focusing on systems that are robust against hallucinations and traceable to authoritative legal sources. First, we propose a unified framework for verified generation in legal AI, linking reasoning, retrieval, and validation around factual reliability. Second, we cast reliability methods into two paradigms of epistemic negotiation, by failure and by conflict, enabling models to recognize and act on their competence limits. Third, we survey the legal-AI landscape and identify challenges for verifiable, governance-native systems. This survey outlines a roadmap for trustworthy legal AI and for reliable reasoning beyond the legal domain.Keywords
All Related Versions
This publication has 46 references indexed in Scilit:
- A framework to assess clinical safety and hallucination rates of LLMs for medical text summarisationnpj Digital Medicine, 2025
- Hallucination‐Free? Assessing the Reliability of Leading AI Legal Research ToolsJournal of Empirical Legal Studies, 2025
- Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the ArtACM Computing Surveys, 2025
- A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open QuestionsACM Transactions on Information Systems, 2025
- LegalReasoner: A Multi-Stage Framework for Legal Judgment Prediction via Large Language Models and Knowledge IntegrationIEEE Access, 2024
- LawLLM: Law Large Language Model for the US Legal System2024
- Calibrated Language Models Must Hallucinate2024
- Survey of Hallucination in Natural Language GenerationACM Computing Surveys, 2023
- COLIEE 2020: Methods for Legal Document Retrieval and Entailment2021
- Model Cards for Model Reporting2019