用自生成提示激发大模型零样本关系抽取潜力
Unleashing the Power of Large Language Models in Zero-shot Relation Extraction via Self-Prompting
- 自动生成多样化合成样本作为上下文提示
- 在多个基准数据集上超越现有方法
- 适合想提升零样本关系抽取效果的研究者
零样本关系抽取（RE）近期研究聚焦于利用大语言模型（LLMs）的零样本能力。然而，现有方法表现不佳，主要因缺乏针对具体句子和关系的详细上下文提示。为此，我们提出Self-Prompting框架，旨在充分挖掘LLMs中嵌入的RE知识。该框架采用三阶段多样性策略，从头生成多个合成样本，封装特定关系。这些生成样本作为上下文学习实例，为LLM提供明确且上下文相关的引导，高效完成关系抽取。在基准数据集上的实验表明，该方法优于现有基于LLM的零样本RE方法。此外，实验验证了生成管道能产出高质量合成数据，有效提升性能。
原文摘要 · Abstract (English)
Recent research in zero-shot Relation Extraction (RE) has focused on using Large Language Models (LLMs) due to their impressive zero-shot capabilities. However, current methods often perform suboptimally, mainly due to a lack of detailed, context-specific prompts needed for understanding various sentences and relations. To address this, we introduce the Self-Prompting framework, a novel method designed to fully harness the embedded RE knowledge within LLMs. Specifically, our framework employs a three-stage diversity approach to prompt LLMs, generating multiple synthetic samples that encapsulate specific relations from scratch. These generated samples act as in-context learning samples, offering explicit and context-specific guidance to efficiently prompt LLMs for RE. Experimental evaluations on benchmark datasets show our approach outperforms existing LLM-based zero-shot RE methods. Additionally, our experiments confirm the effectiveness of our generation pipeline in producing high-quality synthetic data that enhances 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。