用对话方式激发大模型潜能，提升零样本命名实体识别性能
DE-NER : Zero-shot Named Entity Recognition via Dialogue Elicitation of Large Language Models
- 通过对话交互引导大模型自动生成标注知识
- 在多个基准上平均提升3.75%的F1分数
- 无需人工设计提示，适合快速部署到新领域
最近的零样本命名实体识别（NER）进展通过将序列标注转化为问答任务，使大语言模型（LLMs）得以自然应用。然而，现有基于LLM的零样本NER方法受限于提示工程与示范设计。为在极少人工干预下解决这些问题，我们提出DE-NER——一种对话式知识挖掘框架，利用大模型的对话能力充分提取其内部编码的知识。实验表明，该方法在多个基准上的零样本设置中优于现有基线，平均提升3.75% F1分。代码已开源：https://github.com/kkkenshi/DE-NER。
原文摘要 · Abstract (English)
Recent advancements of zero-shot Named Entity Recognition (NER) establish strong baselines by formulating sequence labeling into question answering where Large Language Models (LLMs) can be naturally adopted. However, existing LLM-based zero-shot NER methods suffer from the limitations of prompt and demonstration engineering. To address these issues with minimal human interventions, we introduce DE-NER, a dialogue elicitation framework which elicits the chatting ability of LLMs to fully extract the knowledge encoded in LLMs. Our experiments demonstrate that the proposed method outperform the competitive baselines in zero-shot settings across multiple benchmarks, with an average improvement of 3.75\% F1 points. Codes are released in https://github.com/kkkenshi/DE-NER.
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。