EventRL: Enhancing Event Extraction with Outcome Supervision for Large Language Models
This addresses event extraction challenges like instruction following and hallucination for LLM users, though it appears incremental as it builds on existing RL and supervision techniques.
EventRL uses reinforcement learning with outcome supervision to improve event extraction in large language models, significantly outperforming methods like Few-Shot Prompting and Supervised Fine-Tuning across models such as GPT-4 and LLaMa.
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.