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.

翻译：话语中事件的结构化抽取对于深入理解交流模式与行为趋势至关重要。事件论元抽取（EAE）作为事件理解的核心任务，旨在为给定事件识别特定角色的文本片段（即论元）。文档级事件论元抽取（DocEAE）聚焦于分布在整个文档中的论元。本研究探索了开源大语言模型（LLMs，即Flan-UL2）在DocEAE任务中的能力。为此，我们提出ULTRA层次化框架，以更经济的方式抽取事件论元——该方法仅需50条标注数据，无需调用昂贵的API接口。该框架同时缓解了LLMs固有的位置偏差问题。ULTRA首先按序读取文档的文本块以生成候选论元集，进而通过自精炼机制学习剔除不相关候选。我们进一步引入LEAFER以解决LLMs在定位论元跨度精确边界时面临的挑战。在精确匹配（EM）指标评估下，ULTRA以9.8%的绝对优势超越了包括强监督模型和ChatGPT在内的强基线模型。