An interpretability framework for Similar case matching

TL;DR

This paper introduces an interpretable framework for Similar Case Matching in legal systems, emphasizing transparency through sentence alignment and conflict resolution, and sets a new benchmark for interpretability in SCM models.

Contribution

The study presents an integrated pipeline with modules for feature extraction, case matching, sentence alignment, and conflict resolution, enhancing interpretability in SCM.

Findings

Framework effectively aligns feature sentences to explain case similarity.

Conflict resolution improves the consistency of matching results.

Establishes a new benchmark for interpretability in legal case matching.

Abstract

Similar Case Matching (SCM) plays a pivotal role in the legal system by facilitating the efficient identification of similar cases for legal professionals. While previous research has primarily concentrated on enhancing the performance of SCM models, the aspect of interpretability has been neglected. To bridge the gap, this study proposes an integrated pipeline framework for interpretable SCM. The framework comprises four modules: judicial feature sentence identification, case matching, feature sentence alignment, and conflict resolution. In contrast to current SCM methods, our framework first extracts feature sentences within a legal case that contain essential information. Then it conducts case matching based on these extracted features. Subsequently, our framework aligns the corresponding sentences in two legal cases to provide evidence of similarity. In instances where the results of case matching and feature sentence alignment exhibit conflicts, the conflict resolution module resolves these inconsistencies. The experimental results show the effectiveness of our proposed framework, establishing a new benchmark for interpretable SCM.