paper-with-me

홈 › Papers

ULTRA: Unleash LLMs' Potential for Event Argument Extraction through Hierarchical Modeling and Pair-wise Refinement

2024-01-24 · Xinliang Frederick Zhang, Carter Blum, Temma Choji, Shalin Shah, Alakananda Vempala

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 the capabilities of open source Large Language Models (LLMs), i.e., Flan-UL2, for the DocEAE task. To this end, we propose ULTRA, a hierarchical framework that extracts event arguments more cost-effectively -- the method needs as few as 50 annotations and doesn't require hitting costly API endpoints. Further, it alleviates the positional bias issue intrinsic to LLMs. ULTRA first sequentially reads text chunks of a document to generate a candidate argument set, upon which ULTRA learns to drop non-pertinent candidates through self-refinement. We further introduce LEAFER to address the challenge LLMs face in locating the exact boundary of an argument span. ULTRA outperforms strong baselines, which include strong supervised models and ChatGPT, by 9.8% when evaluated by the exact match (EM) metric.

📄 PDF Abstract BibTeX arXiv:2401.13218

Code (0)

등록된 구현이 없습니다.

Tasks

Event Argument Extraction

Similar Papers 제목 키워드 기반

MAVEN-Arg: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation

2023-11-15 · Xiaozhi Wang, Hao Peng, Yong Guan, Kaisheng Zeng 외

Understanding events in texts is a core objective of natural language understanding, which requires detecting event occurrences, extracting event arguments, and analyzing inter-event relationships. However, due to the an…

AllEvent Argument ExtractionEvent DetectionEvent Relation Extraction+2

Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem

2025-06-03 · YuBo Wang, Ping Nie, Kai Zou, Lijun Wu 외

We have witnessed that strong LLMs like Qwen-Math, MiMo, and Phi-4 possess immense reasoning potential inherited from the pre-training stage. With reinforcement learning (RL), these models can improve dramatically on rea…

GPUMathReinforcement Learning (RL)

LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

2024-08-13 · Yushi Bai, Jiajie Zhang, Xin Lv, Linzhi Zheng 외

Current long context large language models (LLMs) can process inputs up to 100,000 tokens, yet struggle to generate outputs exceeding even a modest length of 2,000 words. Through controlled experiments, we find that the …

REGen: A Reliable Evaluation Framework for Generative Event Argument Extraction

2025-02-24 · Omar Sharif, Joseph Gatto, Madhusudan Basak, Sarah M. Preum

Event argument extraction identifies arguments for predefined event roles in text. Traditional evaluations rely on exact match (EM), requiring predicted arguments to match annotated spans exactly. However, this approach …

Event Argument Extractionvalid

BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation

2024-02-16 · Dayou Du, Yijia Zhang, Shijie Cao, Jiaqi Guo 외

The upscaling of Large Language Models (LLMs) has yielded impressive advances in natural language processing, yet it also poses significant deployment challenges. Weight quantization has emerged as a widely embraced solu…

Knowledge DistillationQuantization