用强化学习动态决定何时调用外部知识，提升实体识别准确率。
NE-R1: Enhancing Named Entity Recognition Model via Reinforcement Learning
- 根据需求自动选择是否检索外部知识，避免冗余
- 在多个数据集上平均提升2.52%的F1值
- 适合需要精准识别冷门实体的场景
命名实体识别（NER）自大型语言模型（LLMs）出现以来取得了显著进展。然而，由于参数化知识不足，长尾和领域特定实体的识别仍具挑战性。检索增强生成（RAG）通过引入外部知识提供了有效解决方案，但在熟悉案例中会引入噪声并增加计算开销。本文提出NE-R1，一种自适应检索增强的NER框架。设计了‘按需检索’机制，并通过两阶段训练方法集成：(1) 多任务指令微调初始化；(2) 带有思维链（CoT）的端到端强化学习优化。为合理权衡参数化知识与外部知识，设计了多维度奖励函数，综合考虑准确率与检索收益。NE-R1在多个基准测试中达到领先性能，在域内评估中平均F1提升2.52%，零样本跨域评估中提升1.18%。
原文摘要 · Abstract (English)
Named Entity Recognition (NER) has achieved substantial progress since the advent of large language models (LLMs). Nevertheless, the recognition of long-tail and domain-specific entities remains challenging due to the deficiency in parametric knowledge. Retrieval-augmented generation (RAG) offers a promising remedy by injecting external knowledge, but it also introduces noise and unnecessary cost when dealing with familiar cases. In this paper, we propose NE-R1, a novel framework for adaptive retrieval-augmented NER. We design a "retrieval-on-demand" mechanism for NER. Then we integrate it into models by a two-stage training method: (1) multi-task instruction tuning initialization; (2) end-to-end RL optimization with CoT. To achieve reasonable selection between parameterized and external knowledge, we design a multi-dimensional reward considering both accuracy and retrieval benefit. NE-R1 achieves state-of-the-art performance on various benchmarks, with an average F1 score gain of 2.52% in in-domain evaluation and 1.18% in zero-shot cross-domain evaluation.
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。