Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models

TL;DR

This paper introduces a novel end-to-end approach for long-form legal question answering using retrieval-augmented large language models, supported by a new expert-annotated dataset in French, aiming to improve legal literacy and model evaluation.

Contribution

It presents a retrieve-then-read pipeline for long-form legal answers and releases the LLeQA dataset, a comprehensive resource for French legal questions and answers.

Findings

Promising performance on automatic evaluation metrics.

Qualitative analysis highlights areas for model refinement.

LLeQA dataset enables rigorous NLP model evaluation in legal domain.

Abstract

Many individuals are likely to face a legal dispute at some point in their lives, but their lack of understanding of how to navigate these complex issues often renders them vulnerable. The advancement of natural language processing opens new avenues for bridging this legal literacy gap through the development of automated legal aid systems. However, existing legal question answering (LQA) approaches often suffer from a narrow scope, being either confined to specific legal domains or limited to brief, uninformative responses. In this work, we propose an end-to-end methodology designed to generate long-form answers to any statutory law questions, utilizing a "retrieve-then-read" pipeline. To support this approach, we introduce and release the Long-form Legal Question Answering (LLeQA) dataset, comprising 1,868 expert-annotated legal questions in the French language, complete with detailed answers rooted in pertinent legal provisions. Our experimental results demonstrate promising performance on automatic evaluation metrics, but a qualitative analysis uncovers areas for refinement. As one of the only comprehensive, expert-annotated long-form LQA dataset, LLeQA has the potential to not only accelerate research towards resolving a significant real-world issue, but also act as a rigorous benchmark for evaluating NLP models in specialized domains. We publicly release our code, data, and models.