ULTRA: Unleash LLMs' Potential for Event Argument Extraction through Hierarchical Modeling and Pair-wise Refinement
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Event Argument ExtractionSimilar Papers 제목 키워드 기반
MAVEN-Arg: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation
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+2Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem
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
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
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 ExtractionvalidBitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation
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