NER Retriever：基于类型感知嵌入的零样本命名实体检索
NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings
AI总结：
针对无预定义类型的即席命名实体检索问题，提出基于大语言模型中间层value向量和轻量对比投影网络的零样本框架NER Retriever，性能优于现有基线，为无模式实体检索提供实用方案。
摘要：
我们提出了NER Retriever，这是一种面向即席命名实体检索的零样本检索框架，该任务是命名实体识别（NER）的一个变体，其感兴趣的实体类型无需预先提供，而是通过用户自定义的类型描述来检索提及对应类型实体的文档。我们的方法不依赖固定模式或微调模型，而是基于大语言模型（LLM）的内部表示，将实体提及和用户提供的开放式类型描述嵌入到同一个共享语义空间中。我们发现，LLM的内部表示，尤其是Transformer中间层的value向量，比常用的顶层嵌入能更有效地编码细粒度类型信息。为优化这些表示，我们训练了一个轻量级对比投影网络，它能对齐类型匹配的实体，同时区分不相关的类型。最终得到的实体嵌入紧凑、具备类型感知能力，非常适合近邻搜索。在三个基准数据集上的评估结果显示，NER Retriever的性能显著优于词汇级和稠密句子级检索基线。我们的研究结果为LLM内部的表示选择提供了实证支持，也为可扩展的无模式实体检索提供了实用解决方案。NER Retriever代码库已在https://github.com/ShacharOr100/ner_retriever公开。
英文摘要：
We present NER Retriever, a zero-shot retrieval framework for ad-hoc Named Entity Retrieval, a variant of Named Entity Recognition (NER), where the types of interest are not provided in advance, and a user-defined type description is used to retrieve documents mentioning entities of that type. Instead of relying on fixed schemas or fine-tuned models, our method builds on internal representations of large language models (LLMs) to embed both entity mentions and user-provided open-ended type descriptions into a shared semantic space. We show that internal representations, specifically the value vectors from mid-layer transformer blocks, encode fine-grained type information more effectively than commonly used top-layer embeddings. To refine these representations, we train a lightweight contrastive projection network that aligns type-compatible entities while separating unrelated types. The resulting entity embeddings are compact, type-aware, and well-suited for nearest-neighbor search. Evaluated on three benchmarks, NER Retriever significantly outperforms both lexical and dense sentence-level retrieval baselines. Our findings provide empirical support for representation selection within LLMs and demonstrate a practical solution for scalable, schema-free entity retrieval. The NER Retriever Codebase is publicly available at https://github.com/ShacharOr100/ner_retriever
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
