ULTRA: Unleash LLMs’ Potential for Event Argument Extraction through Hierarchical Modeling and Pair-wise Self-Refinement
Xinliang Frederick Zhang, Carter Blum, Temma Choji, Shalin Shah, Alakananda Vempala
Abstract
Structural extraction of events within discourse is critical since it avails a deeper understanding of communication patterns and behavior trends. Event argument extraction (EAE), at the core of event-centric understanding, is the task of identifying role-specific text spans (i.e., arguments) for a given event. Document-level EAE (DocEAE) focuses on arguments that are scattered across an entire document. In this work, we explore open-source Large Language Models (LLMs) for DocEAE, and propose ULTRA, a hierarchical framework that extracts event arguments more cost-effectively. Further, it alleviates the positional bias issue intrinsic to LLMs. ULTRA sequentially reads text chunks of a document to generate a candidate argument set, upon which non-pertinent candidates are dropped through self-refinement. We introduce LEAFER to address the challenge LLMs face in locating the exact boundary of an argument. ULTRA outperforms strong baselines, including strong supervised models and ChatGPT, by 9.8% when evaluated by Exact Match (EM).- Anthology ID:
- 2024.findings-acl.487
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2024
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8172–8185
- Language:
- URL:
- https://preview.aclanthology.org/add_missing_videos/2024.findings-acl.487/
- DOI:
- 10.18653/v1/2024.findings-acl.487
- Cite (ACL):
- Xinliang Frederick Zhang, Carter Blum, Temma Choji, Shalin Shah, and Alakananda Vempala. 2024. ULTRA: Unleash LLMs’ Potential for Event Argument Extraction through Hierarchical Modeling and Pair-wise Self-Refinement. In Findings of the Association for Computational Linguistics: ACL 2024, pages 8172–8185, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- ULTRA: Unleash LLMs’ Potential for Event Argument Extraction through Hierarchical Modeling and Pair-wise Self-Refinement (Zhang et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/add_missing_videos/2024.findings-acl.487.pdf