LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning

TL;DR

LegalReasoner enhances legal judgment prediction by implementing step-wise verification and correction, improving reasoning accuracy and reliability in complex legal cases through detailed dispute point analysis and process validation.

Contribution

It introduces a novel step-wise verification and correction framework for legal reasoning, supported by a new annotated dataset, LegalHK, for training and evaluation.

Findings

Significantly improves decision concordance from 72.37% to 80.27%.

Effectively identifies and corrects logical errors in legal reasoning.

Demonstrates robustness on a large-scale Hong Kong court case dataset.

Abstract

Legal judgment prediction (LJP) aims to function as a judge by making final rulings based on case claims and facts, which plays a vital role in the judicial domain for supporting court decision-making and improving judicial efficiency. However, existing methods often struggle with logical errors when conducting complex legal reasoning. We propose LegalReasoner, which enhances LJP reliability through step-wise verification and correction of the reasoning process. Specifically, it first identifies dispute points to decompose complex cases, and then conducts step-wise reasoning while employing a process verifier to validate each step's logic from correctness, progressiveness, and potential perspectives. When errors are detected, expert-designed attribution and resolution strategies are applied for correction. To fine-tune LegalReasoner, we release the LegalHK dataset, containing 58,130 Hong Kong court cases with detailed annotations of dispute points, step-by-step reasoning chains, and process verification labels. Experiments demonstrate that LegalReasoner significantly improves concordance with court decisions from 72.37 to 80.27 on LLAMA-3.1-70B. The data is available at https://huggingface.co/datasets/weijiezz/LegalHK.