LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation

TL;DR

LeCoDe introduces a large, authentic multi-turn legal consultation dataset and a comprehensive evaluation framework to assess and improve LLMs' legal dialogue capabilities in real-world scenarios.

Contribution

The paper presents LeCoDe, a novel benchmark dataset of real-world legal consultations and a multi-metric evaluation framework for LLMs' legal dialogue performance.

Findings

State-of-the-art models like GPT-4 achieve only 39.8% recall in clarification tasks.

Models attain up to 59% in overall advice quality, indicating room for improvement.

The study highlights significant challenges in deploying LLMs for professional legal consultations.

Abstract

Legal consultation is essential for safeguarding individual rights and ensuring access to justice, yet remains costly and inaccessible to many individuals due to the shortage of professionals. While recent advances in Large Language Models (LLMs) offer a promising path toward scalable, low-cost legal assistance, current systems fall short in handling the interactive and knowledge-intensive nature of real-world consultations. To address these challenges, we introduce LeCoDe, a real-world multi-turn benchmark dataset comprising 3,696 legal consultation dialogues with 110,008 dialogue turns, designed to evaluate and improve LLMs' legal consultation capability. With LeCoDe, we innovatively collect live-streamed consultations from short-video platforms, providing authentic multi-turn legal consultation dialogues. The rigorous annotation by legal experts further enhances the dataset with professional insights and expertise. Furthermore, we propose a comprehensive evaluation framework that assesses LLMs' consultation capabilities in terms of (1) clarification capability and (2) professional advice quality. This unified framework incorporates 12 metrics across two dimensions. Through extensive experiments on various general and domain-specific LLMs, our results reveal significant challenges in this task, with even state-of-the-art models like GPT-4 achieving only 39.8% recall for clarification and 59% overall score for advice quality, highlighting the complexity of professional consultation scenarios. Based on these findings, we further explore several strategies to enhance LLMs' legal consultation abilities. Our benchmark contributes to advancing research in legal domain dialogue systems, particularly in simulating more real-world user-expert interactions.