Context-Aware Legal Citation Recommendation using Deep Learning

TL;DR

This paper presents a deep learning-based citation recommendation system for legal texts, demonstrating that context-aware models like RoBERTa and BiLSTM improve citation suggestions, with deep models performing comparably to traditional methods.

Contribution

It introduces a novel application of deep neural models for legal citation recommendation, comparing their performance with traditional methods and analyzing their behavior across contexts.

Findings

Deep neural models achieve decent performance in citation recommendation.

Contextual information enhances recommendation accuracy.

RoBERTa does not outperform recurrent models despite pretraining benefits.

Abstract

Lawyers and judges spend a large amount of time researching the proper legal authority to cite while drafting decisions. In this paper, we develop a citation recommendation tool that can help improve efficiency in the process of opinion drafting. We train four types of machine learning models, including a citation-list based method (collaborative filtering) and three context-based methods (text similarity, BiLSTM and RoBERTa classifiers). Our experiments show that leveraging local textual context improves recommendation, and that deep neural models achieve decent performance. We show that non-deep text-based methods benefit from access to structured case metadata, but deep models only benefit from such access when predicting from context of insufficient length. We also find that, even after extensive training, RoBERTa does not outperform a recurrent neural model, despite its benefits of pretraining. Our behavior analysis of the RoBERTa model further shows that predictive performance is stable across time and citation classes.