用标注指南指导大模型提取事件，提升小样本和少见事件效果。
Instruction-Tuning LLMs for Event Extraction with Annotation Guidelines
- 用文本描述事件类型和要素作为指令微调模型
- 数据充足时显著提升跨模式泛化与罕见事件识别
- 适合做事件抽取且标注数据少的场景
本文研究在事件抽取任务中，使用人工编写和机器生成的标注指南（即事件类型与论元的文本说明）对大语言模型进行指令微调的效果。我们在全量数据和低数据设置下进行了多组实验。结果表明，在训练数据充足时，标注指南展现出显著潜力，能有效提升模型在跨模式泛化能力以及低频事件类型上的表现。
原文摘要 · Abstract (English)
In this work, we study the effect of annotation guidelines -- textual descriptions of event types and arguments, when instruction-tuning large language models for event extraction. We conducted a series of experiments with both human-provided and machine-generated guidelines in both full- and low-data settings. Our results demonstrate the promise of annotation guidelines when there is a decent amount of training data and highlight its effectiveness in improving cross-schema generalization and low-frequency event-type performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。