LegalCore: A Dataset for Event Coreference Resolution in Legal Documents

TL;DR

LegalCore is the first comprehensive dataset for event coreference resolution in legal documents, revealing dense event mentions and long-distance links, and challenging current large language models in this domain.

Contribution

This paper introduces LegalCore, the first dataset for event coreference in legal texts, and benchmarks LLMs, highlighting their limitations in this specialized domain.

Findings

Legal documents have dense event mentions and long-distance coreference links.

State-of-the-art LLMs perform poorly on legal event coreference tasks.

LegalCore dataset is significantly longer and more complex than news-based datasets.

Abstract

Recognizing events and their coreferential mentions in a document is essential for understanding semantic meanings of text. The existing research on event coreference resolution is mostly limited to news articles. In this paper, we present the first dataset for the legal domain, LegalCore, which has been annotated with comprehensive event and event coreference information. The legal contract documents we annotated in this dataset are several times longer than news articles, with an average length of around 25k tokens per document. The annotations show that legal documents have dense event mentions and feature both short-distance and super long-distance coreference links between event mentions. We further benchmark mainstream Large Language Models (LLMs) on this dataset for both event detection and event coreference resolution tasks, and find that this dataset poses significant challenges for state-of-the-art open-source and proprietary LLMs, which perform significantly worse than a supervised baseline. We will publish the dataset as well as the code.