Enhancing Document-level Argument Extraction with Definition-augmented Heuristic-driven Prompting for LLMs
This work addresses document-level EAE for natural language processing applications, offering an incremental improvement by combining known techniques like Chain-of-Thought with new prompting strategies.
The paper tackled the challenge of document-level Event Argument Extraction (EAE) by proposing a Definition-augmented Heuristic-driven Prompting (DHP) method, which integrates definitions and heuristic rules to guide Large Language Models, resulting in improved performance over existing methods and reduced reliance on annotated datasets.
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.