Multi-LexSum: Real-World Summaries of Civil Rights Lawsuits at Multiple Granularities

TL;DR

Multi-LexSum introduces a large, multi-granularity dataset of civil rights lawsuit summaries, highlighting the challenges of current models in producing high-quality summaries for complex, lengthy legal documents.

Contribution

The paper presents Multi-LexSum, a novel dataset of 9,280 expert summaries at multiple granularities for civil rights lawsuits, enabling research on multi-document summarization of lengthy legal texts.

Findings

State-of-the-art models perform poorly on the dataset

High-quality, expert-authored summaries reveal the complexity of legal summarization

Multi-LexSum facilitates future research in summarization methods

Abstract

With the advent of large language models, methods for abstractive summarization have made great strides, creating potential for use in applications to aid knowledge workers processing unwieldy document collections. One such setting is the Civil Rights Litigation Clearinghouse (CRLC) (https://clearinghouse.net),which posts information about large-scale civil rights lawsuits, serving lawyers, scholars, and the general public. Today, summarization in the CRLC requires extensive training of lawyers and law students who spend hours per case understanding multiple relevant documents in order to produce high-quality summaries of key events and outcomes. Motivated by this ongoing real-world summarization effort, we introduce Multi-LexSum, a collection of 9,280 expert-authored summaries drawn from ongoing CRLC writing. Multi-LexSum presents a challenging multi-document summarization task given the length of the source documents, often exceeding two hundred pages per case. Furthermore, Multi-LexSum is distinct from other datasets in its multiple target summaries, each at a different granularity (ranging from one-sentence "extreme" summaries to multi-paragraph narrations of over five hundred words). We present extensive analysis demonstrating that despite the high-quality summaries in the training data (adhering to strict content and style guidelines), state-of-the-art summarization models perform poorly on this task. We release Multi-LexSum for further research in summarization methods as well as to facilitate development of applications to assist in the CRLC's mission at https://multilexsum.github.io.