用定义和规则引导大模型，提升文档级论点抽取准确率。
Enhancing Document-level Argument Extraction with Definition-augmented Heuristic-driven Prompting for LLMs
- 结合论点定义与启发式规则，引导大模型推理
- 在多个数据集上优于现有提示方法与少样本学习
- 减少对大规模标注数据依赖，适合资源有限场景
事件论点抽取（EAE）对于从非结构化文本中提取结构化信息至关重要，但文档级EAE因现实场景复杂性仍具挑战。本文提出一种新型定义增强型启发式提示方法（DHP），通过整合论点抽取相关定义与启发式规则，指导大语言模型（LLMs）的抽取过程，降低错误传播并提升任务准确性。同时采用思维链（CoT）模拟人类推理，将复杂问题分解为可管理的子问题。实验表明，该方法在文档级EAE数据集上相较现有提示方法及少样本监督学习均取得显著性能提升。DHP增强了LLMs的泛化能力，降低了对大规模标注数据的依赖，为文档级EAE提供了新研究视角。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。