Saved in:
Bibliographic Details
Main Authors: Wang, Sijia, Huang, Lifu
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.12197
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914837903179776
author Wang, Sijia
Huang, Lifu
author_facet Wang, Sijia
Huang, Lifu
contents We propose a multi-agent debate as optimization (DAO) system for event extraction, where the primary objective is to iteratively refine the large language models (LLMs) outputs through debating without parameter tuning. In DAO, we introduce two novel modules: the Diverse-RAG (DRAG) module and the Adaptive Conformal Prediction (AdaCP) module. DRAG systematically retrieves supporting information that best fits the debate discussion, while AdaCP enhances the accuracy and reliability of event extraction by effectively rejecting less promising answers. Experimental results demonstrate a significant reduction in the performance gap between supervised approaches and tuning-free LLM-based methods by 18.1% and 17.8% on ACE05 and 17.9% and 15.2% on CASIE for event detection and argument extraction respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2406_12197
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Debate as Optimization: Adaptive Conformal Prediction and Diverse Retrieval for Event Extraction
Wang, Sijia
Huang, Lifu
Computation and Language
Artificial Intelligence
We propose a multi-agent debate as optimization (DAO) system for event extraction, where the primary objective is to iteratively refine the large language models (LLMs) outputs through debating without parameter tuning. In DAO, we introduce two novel modules: the Diverse-RAG (DRAG) module and the Adaptive Conformal Prediction (AdaCP) module. DRAG systematically retrieves supporting information that best fits the debate discussion, while AdaCP enhances the accuracy and reliability of event extraction by effectively rejecting less promising answers. Experimental results demonstrate a significant reduction in the performance gap between supervised approaches and tuning-free LLM-based methods by 18.1% and 17.8% on ACE05 and 17.9% and 15.2% on CASIE for event detection and argument extraction respectively.
title Debate as Optimization: Adaptive Conformal Prediction and Diverse Retrieval for Event Extraction
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2406.12197