NE-R1: Enhancing Named Entity Recognition Model via Reinforcement Learning

  • 类型:arxiv
  • 标识:2609.02366
  • 链接:http://arxiv.org/abs/2609.02366v1
  • 主分类:rag
  • 形态:method
  • TLDR: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 int
  • 待LLM分类:否
  • 来源文件
  • /inbox/tom/_candidates/2026-09-03-agent-rag-longcontext-candidates.json