URA-NER：一种面向低资源命名实体识别的统一检索增强框架，具备检索对齐与不确定性降低机制
URA-NER: A Unified Retrieval-Augmented Framework with Retrieval Alignment and Uncertainty Reduction for Low-Resource NER
查看机构详情
- Beijing Institute of Technology（北京理工大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
提出统一检索增强框架URA-NER，通过渐进粒度检索、模型感知表示增强和推理感知知识验证，解决低资源NER中的检索错位与生成不确定性问题，显著提升LLM性能。
中文摘要 AI 辅助
基于大型语言模型（LLM）的上下文学习（ICL）在缓解命名实体识别（NER）中因标注数据有限而导致的性能瓶颈方面展现出巨大潜力。然而，现有方法仍面临检索错位和生成不确定性问题，其性能高度依赖LLM的能力。随着LLM参数规模的减小，其在少样本场景下的性能显著下降。本文提出了一种新颖的统一检索增强框架URA-NER，包含三个关键组件：渐进粒度检索（PGR）、模型感知表示增强（MaRE）和推理感知知识验证（RaKV）。PGR是一种两阶段检索机制，实现阶段对齐：首先基于查询的全局语义检索用于跨度检测的演示，然后基于特定实体上下文检索用于类型分类的演示，提供细粒度的局部信息。此外，MaRE利用实体预识别来指导表示的构建，确保查询和演示在LLM的语义空间和注意力模式中对齐。为缓解生成不确定性，我们提出RaKV，一种闭环的“生成-检索-验证”过程，它显式化LLM的推理路径，利用这些路径检索外部知识，并将知识重组为与原始推理路径对齐的验证证据。我们在多个低资源NER数据集上进行了广泛实验。结果表明，URA-NER显著增强了LLM在低资源设置下的性能，对较小LLM的提升尤为明显，在多个基准上取得了新的最先进结果。
英文摘要
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.
