In this study, we present EventRL, a reinforcement learning approach
developed to enhance event extraction for large language models (LLMs). EventRL
utilizes outcome supervision with specific reward functions to tackle prevalent
challenges in LLMs, such as instruction following and hallucination, manifested
as the mismatch of event structure and the generation of undefined event types.
We evaluate EventRL against existing methods like Few-Shot Prompting (FSP)
(based on GPT4) and Supervised Fine-Tuning (SFT) across various LLMs, including
GPT-4, LLaMa, and CodeLLaMa models. Our findings show that EventRL
significantly outperforms these conventional approaches by improving the
performance in identifying and structuring events, particularly in handling
novel event types. The study emphasizes the critical role of reward function
selection and demonstrates the benefits of incorporating code data for better
event extraction. While increasing model size leads to higher accuracy,
maintaining the ability to generalize is essential to avoid overfitting.

本研究提出了 EventRL，一种强化学习方法，用于改进大型语言模型（LLMs）的事件提取。通过特定的奖励函数和结果监督，EventRL 有效解决了 LLMs 中的指令遵循和虚构等问题，改进了事件识别和结构化的性能，特别是在处理新事件类型方面。研究强调了奖励函数选择的关键作用，并展示了在事件提取中引入代码数据的益处。增加模型大小可以提高准确性，但保持泛化能力至关重要以避免过拟合。