Explainable Legal Case Matching via Inverse Optimal Transport-based Rationale Extraction

TL;DR

This paper introduces IOT-Match, an explainable legal case matching method using inverse optimal transport to extract rationales based on semantics and legal features, improving explainability and robustness.

Contribution

The paper proposes a novel IOT-Match framework that leverages inverse optimal transport for explainable legal case matching, including rationale extraction and explanation generation.

Findings

Outperforms state-of-the-art methods on CAIL and ELAM datasets.

Effectively extracts rationales based on semantics and legal characteristics.

Robust to label insufficiency in legal case matching tasks.

Abstract

As an essential operation of legal retrieval, legal case matching plays a central role in intelligent legal systems. This task has a high demand on the explainability of matching results because of its critical impacts on downstream applications -- the matched legal cases may provide supportive evidence for the judgments of target cases and thus influence the fairness and justice of legal decisions. Focusing on this challenging task, we propose a novel and explainable method, namely \textit{IOT-Match}, with the help of computational optimal transport, which formulates the legal case matching problem as an inverse optimal transport (IOT) problem. Different from most existing methods, which merely focus on the sentence-level semantic similarity between legal cases, our IOT-Match learns to extract rationales from paired legal cases based on both semantics and legal characteristics of their sentences. The extracted rationales are further applied to generate faithful explanations and conduct matching. Moreover, the proposed IOT-Match is robust to the alignment label insufficiency issue commonly in practical legal case matching tasks, which is suitable for both supervised and semi-supervised learning paradigms. To demonstrate the superiority of our IOT-Match method and construct a benchmark of explainable legal case matching task, we not only extend the well-known Challenge of AI in Law (CAIL) dataset but also build a new Explainable Legal cAse Matching (ELAM) dataset, which contains lots of legal cases with detailed and explainable annotations. Experiments on these two datasets show that our IOT-Match outperforms state-of-the-art methods consistently on matching prediction, rationale extraction, and explanation generation.