Enhancing Document-level Argument Extraction with Definition-augmented Heuristic-driven Prompting for LLMs

TL;DR

This paper introduces a novel Definition-augmented Heuristic-driven Prompting method that improves Large Language Models' performance in document-level Event Argument Extraction by integrating definitions, heuristics, and Chain-of-Thought reasoning.

Contribution

It presents a new prompting approach combining definitions, heuristics, and CoT to enhance LLMs for document-level EAE, reducing reliance on annotated data.

Findings

Improved performance over existing prompting methods

Enhanced generalization capability of LLMs

Reduced dependence on large annotated datasets

Abstract

Event Argument Extraction (EAE) is pivotal for extracting structured information from unstructured text, yet it remains challenging due to the complexity of real-world document-level EAE. We propose a novel Definition-augmented Heuristic-driven Prompting (DHP) method to enhance the performance of Large Language Models (LLMs) in document-level EAE. Our method integrates argument extraction-related definitions and heuristic rules to guide the extraction process, reducing error propagation and improving task accuracy. We also employ the Chain-of-Thought (CoT) method to simulate human reasoning, breaking down complex problems into manageable sub-problems. Experiments have shown that our method achieves a certain improvement in performance over existing prompting methods and few-shot supervised learning on document-level EAE datasets. The DHP method enhances the generalization capability of LLMs and reduces reliance on large annotated datasets, offering a novel research perspective for document-level EAE.