LePaRD: A Large-Scale Dataset of Judges Citing Precedents

TL;DR

LePaRD is a large-scale dataset of U.S. federal judicial citations designed to advance legal passage prediction, a complex task involving retrieving relevant legal precedents to support legal reasoning.

Contribution

The paper introduces LePaRD, a comprehensive dataset for legal passage prediction, and evaluates various retrieval methods, highlighting classification as the most effective approach.

Findings

Classification performs best among evaluated retrieval methods.

Legal passage prediction remains a challenging task with significant room for improvement.

The dataset will be publicly available to foster further research.

Abstract

We present the Legal Passage Retrieval Dataset LePaRD. LePaRD is a massive collection of U.S. federal judicial citations to precedent in context. The dataset aims to facilitate work on legal passage prediction, a challenging practice-oriented legal retrieval and reasoning task. Legal passage prediction seeks to predict relevant passages from precedential court decisions given the context of a legal argument. We extensively evaluate various retrieval approaches on LePaRD, and find that classification appears to work best. However, we note that legal precedent prediction is a difficult task, and there remains significant room for improvement. We hope that by publishing LePaRD, we will encourage others to engage with a legal NLP task that promises to help expand access to justice by reducing the burden associated with legal research. A subset of the LePaRD dataset is freely available and the whole dataset will be released upon publication.