# URA-NER: A Unified Retrieval-Augmented Framework with Retrieval Alignment and Uncertainty Reduction for Low-Resource NER

arXiv: https://arxiv.org/abs/2609.24372 · HTML: https://mlsanity.com/paper/2609.24372/

## 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 8 of its 42 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)

## Builds on (most cited first, 8 of 8)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition](https://mlsanity.com/paper/2308.03279/) (2023)
- [PromptNER: Prompting For Named Entity Recognition](https://mlsanity.com/paper/2305.15444/) (2023)
- [LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity Recognition](https://mlsanity.com/paper/2402.14568/) (2024)
- [Leveraging Large Language Models for Enhanced NLP Task Performance through Knowledge Distillation and Optimized Training Strategies](https://mlsanity.com/paper/2402.09282/) (2024)
- [Transformer-based Named Entity Recognition with Combined Data Representation](https://mlsanity.com/paper/2406.17474/) (2024)
- [Retrieval-Enhanced Named Entity Recognition](https://mlsanity.com/paper/2410.13118/) (2024)

## Abstract (arXiv)

In-context learning (ICL) based on large language models (LLMs) has shown promising potential in alleviating performance bottlenecks caused by the limited availability of annotated data in Named Entity Recognition (NER). However, existing methods still face issues of retrieval misalignment and generation uncertainty, making their performance heavily dependent on the LLM's capabilities. As the parameter scale of LLMs decreases, their performance in few-shot settings deteriorates significantly. In this paper, we propose a novel unified retrieval-augmented framework, URA-NER, including three key components: Progressive Granularity Retrieval (PGR), Model-aware Representation Enhancement (MaRE), and Reason-aware Knowledge Verification. PGR is a two-stage retrieval mechanism that achieves stage alignment. It first retrieves demonstrations for span detection based on the query's global semantics, and then for type classification based on the specific entity context, providing fine-grained local information. Moreover, MaRE employs entity pre-recognition to guide the construction of representations, ensuring the query and demonstrations are aligned within the LLM's semantic space and attention pattern. In addition, to mitigate generation uncertainty, we propose RaKV, a closed-loop "generation-retrieval-verification" process. It explicates the LLM's reasoning paths, leverages them for the retrieval of external knowledge, and reorganizes the knowledge into verification evidence aligned with the original reasoning paths. We conduct extensive experiments on multiple low-resource NER datasets. Results demonstrate that URA-NER significantly enhances the performance of LLMs under low-resource settings, with particularly pronounced gains for smaller LLMs, achieving new state-of-the-art results on several benchmarks.