SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.11430 · 2024

EventRL: Enhancing Event Extraction with Outcome Supervision for Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.11430")
get_code_for_paper("2402.11430")
have("2402.11430")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.11430.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.11430.svg)](https://syntology.ai/paper/2402.11430)

Connect an agent — have() is free.