When Large Language Models Meet Law: Dual-Lens Taxonomy, Technical Advances, and Ethical Governance

TL;DR

This paper provides a comprehensive review of how large language models are applied in the legal domain, introducing a dual-lens taxonomy, discussing technical advances, and addressing ethical challenges to guide future research and practice.

Contribution

It introduces an innovative dual-lens taxonomy for legal LLMs, unifies research frameworks, and proposes a technical roadmap for advancing legal AI applications.

Findings

Transformer-based LLMs show emergent legal reasoning capabilities

Technical innovations improve task generalization and reasoning formalization

Identifies key challenges like hallucination and explainability in legal LLMs

Abstract

This paper establishes the first comprehensive review of Large Language Models (LLMs) applied within the legal domain. It pioneers an innovative dual lens taxonomy that integrates legal reasoning frameworks and professional ontologies to systematically unify historical research and contemporary breakthroughs. Transformer-based LLMs, which exhibit emergent capabilities such as contextual reasoning and generative argumentation, surmount traditional limitations by dynamically capturing legal semantics and unifying evidence reasoning. Significant progress is documented in task generalization, reasoning formalization, workflow integration, and addressing core challenges in text processing, knowledge integration, and evaluation rigor via technical innovations like sparse attention mechanisms and mixture-of-experts architectures. However, widespread adoption of LLM introduces critical challenges: hallucination, explainability deficits, jurisdictional adaptation difficulties, and ethical asymmetry. This review proposes a novel taxonomy that maps legal roles to NLP subtasks and computationally implements the Toulmin argumentation framework, thus systematizing advances in reasoning, retrieval, prediction, and dispute resolution. It identifies key frontiers including low-resource systems, multimodal evidence integration, and dynamic rebuttal handling. Ultimately, this work provides both a technical roadmap for researchers and a conceptual framework for practitioners navigating the algorithmic future, laying a robust foundation for the next era of legal artificial intelligence. We have created a GitHub repository to index the relevant papers: https://github.com/Kilimajaro/LLMs_Meet_Law.