Problem
Research questions and friction points this paper is trying to address.
Named Entity Recognition
Long-tail Entities
Domain-specific Entities
Retrieval-augmented Generation
External Knowledge
NE-R1: Enhancing Named Entity Recognition Model via Reinforcement Learning
🤖 AI Summary
本文提出NE-R1框架，通过强化学习和按需检索机制解决长尾及领域特定实体识别问题，提高了模型性能。
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
retrieval-on-demand
multi-task instruction tuning
end-to-end RL optimization with CoT
multi-dimensional reward
🔎 Similar Papers
No similar papers found.
