LexAbSumm: Aspect-based Summarization of Legal Decisions

TL;DR

LexAbSumm is a new dataset for aspect-based summarization of legal decisions, aiming to generate more tailored summaries for legal professionals by focusing on specific aspects of legal judgments.

Contribution

The paper introduces LexAbSumm, a novel dataset for aspect-based legal summarization, and evaluates models highlighting challenges in aspect-specific summarization of long legal texts.

Findings

Models struggle to produce aspect-specific summaries.

LexAbSumm enables targeted research in legal document summarization.

The dataset facilitates future advancements in legal NLP tasks.

Abstract

Legal professionals frequently encounter long legal judgments that hold critical insights for their work. While recent advances have led to automated summarization solutions for legal documents, they typically provide generic summaries, which may not meet the diverse information needs of users. To address this gap, we introduce LexAbSumm, a novel dataset designed for aspect-based summarization of legal case decisions, sourced from the European Court of Human Rights jurisdiction. We evaluate several abstractive summarization models tailored for longer documents on LexAbSumm, revealing a challenge in conditioning these models to produce aspect-specific summaries. We release LexAbSum to facilitate research in aspect-based summarization for legal domain.