mlsanityData to 14 Oct 2026

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

arXiv 2609.02366 ↗First posted 2 Sep 2026cs.CL cs.AIcited by 0

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 31 of its 52 references that are in the map. First posted on arXiv 2 Sep 2026.

Builds on

31 of 52 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Improving Few-Shot Cross-Domain Named Entity Recognition by Instruction Tuning a Word-Embedding based Retrieval Augmented Large Language Model1 Nov
  2. 2023In-Context Retrieval-Augmented Language Models31 Jan

Other references · 29

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  5. 2022A Survey on In-context Learningcited by 721
  6. 2016Neural Architectures for Named Entity Recognitioncited by 550
  7. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  8. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  9. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  10. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  11. 2016End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRFcited by 341
  12. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
17 more
  1. 2022Unified Structure Generation for Universal Information Extractioncited by 221
  2. 2022Demystifying Prompts in Language Models via Perplexity Estimationcited by 216
  3. 2023GPT-NER: Named Entity Recognition via Large Language Modelscited by 160
  4. 2023GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extractioncited by 119
  5. 2020CrossNER: Evaluating Cross-Domain Named Entity Recognitioncited by 104
  6. 2023GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformercited by 88
  7. 2024Unfamiliar Finetuning Examples Control How Language Models Hallucinatecited by 87
  8. 2023Empirical Study of Zero-Shot NER with ChatGPTcited by 60
  9. 2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQLcited by 59
  10. 2025MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learningcited by 48
  11. 2020Coach: A Coarse-to-Fine Approach for Cross-domain Slot Fillingcited by 38
  12. 2024NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Datacited by 34
  13. 2021LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Promptingcited by 27
  14. 2025TruthfulRAG: Resolving Factual-level Conflicts in Retrieval-Augmented Generation with Knowledge Graphscited by 12
  15. 2023One Model for All Domains: Collaborative Domain-Prefix Tuning for Cross-Domain NERcited by 11
  16. 2024Cross-domain Named Entity Recognition via Graph Matchingcited by 5
  17. 2025ALLabel: Three-stage Active Learning for LLM-based Entity Recognition using Demonstration Retrievalcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Retrieval Augmented Instruction Tuning for Open NER with Large Language Models
  2. 2022kNN-NER: Named Entity Recognition with Nearest Neighbor Search
  3. 2024Recent Advances in Named Entity Recognition: A Comprehensive Survey and Comparative Study
  4. 2026URA-NER: A Unified Retrieval-Augmented Framework with Retrieval Alignment and Uncertainty Reduction for Low-Resource NER
  5. 2021Reinforced Iterative Knowledge Distillation for Cross-Lingual Named Entity Recognition
  6. 2022SCL-RAI: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER
  7. 2023DAMO-NLP at SemEval-2023 Task 2: A Unified Retrieval-augmented System for Multilingual Named Entity Recognition
  8. 2024Rethinking Negative Instances for Generative Named Entity Recognition