Debate as Optimization: Adaptive Conformal Prediction and Diverse Retrieval for Event Extraction

Sijia Wang, Lifu Huang


Abstract
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.
Anthology ID:
2024.findings-emnlp.958
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16422–16435
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.958/
DOI:
10.18653/v1/2024.findings-emnlp.958
Bibkey:
Cite (ACL):
Sijia Wang and Lifu Huang. 2024. Debate as Optimization: Adaptive Conformal Prediction and Diverse Retrieval for Event Extraction. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16422–16435, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Debate as Optimization: Adaptive Conformal Prediction and Diverse Retrieval for Event Extraction (Wang & Huang, Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.958.pdf