Large Language Models for Legal Reasoning and Practice: Retrieval, Interaction, Evaluation, and Ethical Deployment

Large Language Models (LLMs) are rapidly reshaping legal information systems, offering new capabilities in legal search, drafting, summarization, evidential analysis, and decision support. Yet their reliable adoption within legal practice requires much more than linguistic competence: legal AI systems must be evaluated, interpretable, ethically aligned, normatively aware, and professionally trustworthy. They must also operate within complex socio-technical systems involving human users, institutional constraints, and increasingly automated legal infrastructures.

This Research Topic invites research advancing the development, evaluation, and ethical deployment of LLMs and NLP systems for legal contexts. We especially seek work that examines how LLMs can support legal practitioners safely, responsibly, and transparently, how meaningful human oversight and interaction can be ensured through human-centered design and Human–Computer Interaction (HCI) principles, and how normative standards, legal reasoning structures, and governance principles can be embedded into AI architectures. Inspired by recent developments presented at JURIX, this call emphasizes:

- legal reasoning and interpretation using LLMs
- retrieval and context management for factual grounding
- structured legal knowledge extraction
- evaluation methodologies for reasoning quality, fairness, and normative alignment
- ethically responsible deployment in legal practice and public administration
- human–AI interaction, explainability, and contestability in legal decision support systems
- LLMs for smart contracts blockchain-based legal processes, and computational legal infrastructures, including the generation, and auditing of executable legal code

By explicitly addressing interaction, governance, and infrastructure-level questions, rather than focusing solely on task performance or application benchmarks, this Research Topic aims to complement and extend existing work on legal LLM applications.

The main aim is to define the scientific foundations of responsible LLM integration in law, including emerging contexts where legal norms are partially automated, executed, or enforced through digital and decentralized systems, while remaining accountable to human judgment and legal institutions.

Article types and fees

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Conceptual Analysis
• Data Report
• Editorial
• FAIR² Data
• FAIR² DATA Direct Submission
• General Commentary
• Hypothesis and Theory
• Methods
• ... View all formats

Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.

Article types

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Conceptual Analysis
• Data Report
• Editorial
• FAIR² Data
• FAIR² DATA Direct Submission
• General Commentary
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• Policy and Practice Reviews
• Review
• Systematic Review
• Technology and Code

Keywords: Large Language Models, Legal Reasoning, Legal Retrieval, Normative Alignment, Legal AI Evaluation, Ethical AI, Responsible Deployment

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.