LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models

TL;DR

LegalBench is a collaboratively developed benchmark comprising 162 legal reasoning tasks designed to evaluate and advance the understanding of large language models' capabilities in legal reasoning, fostering interdisciplinary dialogue.

Contribution

This paper introduces LegalBench, a new legal reasoning benchmark built with expert input, linking legal frameworks to LLM evaluation, and providing a platform for comprehensive legal AI research.

Findings

LegalBench covers six types of legal reasoning.

20 LLMs were empirically evaluated on the benchmark.

LegalBench facilitates interdisciplinary discussions on legal AI.

Abstract

The advent of large language models (LLMs) and their adoption by the legal community has given rise to the question: what types of legal reasoning can LLMs perform? To enable greater study of this question, we present LegalBench: a collaboratively constructed legal reasoning benchmark consisting of 162 tasks covering six different types of legal reasoning. LegalBench was built through an interdisciplinary process, in which we collected tasks designed and hand-crafted by legal professionals. Because these subject matter experts took a leading role in construction, tasks either measure legal reasoning capabilities that are practically useful, or measure reasoning skills that lawyers find interesting. To enable cross-disciplinary conversations about LLMs in the law, we additionally show how popular legal frameworks for describing legal reasoning -- which distinguish between its many forms -- correspond to LegalBench tasks, thus giving lawyers and LLM developers a common vocabulary. This paper describes LegalBench, presents an empirical evaluation of 20 open-source and commercial LLMs, and illustrates the types of research explorations LegalBench enables.