LePREC: Reasoning as Classification over Structured Factors for Assessing Relevance of Legal Issues

TL;DR

This paper introduces LePREC, a neuro-symbolic framework that improves legal issue relevance assessment by combining neural fact extraction with structured reasoning, achieving significant accuracy gains over LLM baselines.

Contribution

LePREC is a novel neuro-symbolic approach that enhances interpretability and data efficiency in legal issue classification compared to end-to-end neural models.

Findings

LePREC improves relevance classification accuracy by 30-40% over LLM baselines.

GPT-4o achieves only 62% precision in legal issue candidate generation.

Structured reasoning with explicit feature weights enhances interpretability.

Abstract

More than half of the global population struggles to meet their civil justice needs due to limited legal resources. While Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, significant challenges remain even at the foundational step of legal issue identification. To investigate LLMs' capabilities in this task, we constructed a dataset from 769 real-world Malaysian Contract Act court cases, using GPT-4o to extract facts and generate candidate legal issues, annotated by senior legal experts, which reveals a critical limitation: while LLMs generate diverse issue candidates, their precision remains inadequate (GPT-4o achieves only 62%). To address this gap, we propose LePREC (Legal Professional-inspired Reasoning Elicitation and Classification), a neuro-symbolic framework combining neural generation with structured statistical reasoning. LePREC consists of: (1) a neuro component leverages LLMs to transform legal descriptions into question-answer pairs representing diverse analytical factors, and (2) a symbolic component applies sparse linear models over these discrete features, learning explicit algebraic weights that identify the most informative reasoning factors. Unlike end-to-end neural approaches, LePREC achieves interpretability through transparent feature weighting while maintaining data efficiency through correlation-based statistical classification. Experiments show a 30-40% improvement over advanced LLM baselines, including GPT-4o and Claude, confirming that correlation-based factor-issue analysis offers a more data-efficient solution for relevance decisions.