CLCYJun 22, 2022

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

MIT
arXiv:2206.10883v366 citationsh-index: 39
Originality Synthesis-oriented
AI Analysis

This work addresses the problem of automating summarization for lawyers, scholars, and the public in civil rights litigation, but it is incremental as it primarily releases a dataset without proposing a new method.

The authors tackled the challenge of summarizing lengthy civil rights lawsuits by introducing Multi-LexSum, a dataset of 9,280 expert-authored summaries at multiple granularities, and found that state-of-the-art summarization models perform poorly on this task despite high-quality training data.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes