From Legal Texts to Defeasible Deontic Logic via LLMs: A Study in Automated Semantic Analysis

2025-06-10

AI Summary

This paper addresses the challenge of automatically translating legal texts into defeasible deontic logic (DDL) formalizations. To this end, it proposes the first large language model (LLM)-driven semantic parsing framework for DDL formalization. Methodologically, the approach integrates prompt engineering, lightweight fine-tuning, and a multi-stage pipeline to perform legal text segmentation, deontic rule extraction, and syntactic/semantic consistency verification. Its key contribution lies in deeply adapting LLM capabilities to the specific requirements of DDL formalization—ensuring both interpretable translation and explicit normative conflict detection. Empirical evaluation on Australian telecommunications consumer protection legislation demonstrates high alignment between LLM-generated DDL specifications and expert annotations (F1 > 0.89), significantly advancing scalable, verifiable formal modeling in legal informatics.

Technology Category

• Knowledge Representation and Reasoning: Description Logics
• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

We present a novel approach to the automated semantic analysis of legal texts using large language models (LLMs), targeting their transformation into formal representations in Defeasible Deontic Logic (DDL). We propose a structured pipeline that segments complex normative language into atomic snippets, extracts deontic rules, and evaluates them for syntactic and semantic coherence. Our methodology is evaluated across various LLM configurations, including prompt engineering strategies, fine-tuned models, and multi-stage pipelines, focusing on legal norms from the Australian Telecommunications Consumer Protections Code. Empirical results demonstrate promising alignment between machine-generated and expert-crafted formalizations, showing that LLMs - particularly when prompted effectively - can significantly contribute to scalable legal informatics.

Problem

• Automate semantic analysis of legal texts using LLMs
• Transform legal texts into Defeasible Deontic Logic representations
• Evaluate LLM effectiveness in formalizing legal norms

Innovation

• LLMs transform legal texts into Defeasible Deontic Logic
• Pipeline segments norms and extracts deontic rules
• Effective prompting enhances LLM legal formalization accuracy