NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings

Or Shachar, Uri Katz, Yoav Goldberg, Oren Glickman


Abstract
We present NER Retriever, a zero-shot retrieval framework for ad-hoc Named Entity Recognition (NER), where 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 pretrained language models (LLMs) to embed both entity mentions and 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 (BM25) and dense (sentence-level) retrieval baselines, particularly in low-context settings. Our findings provide empirical support for representation selection within LLMs and demonstrate a practical solution for scalable, schema-free entity retrieval.
Anthology ID:
2025.findings-emnlp.597
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11175–11186
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.597/
DOI:
Bibkey:
Cite (ACL):
Or Shachar, Uri Katz, Yoav Goldberg, and Oren Glickman. 2025. NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 11175–11186, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings (Shachar et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.597.pdf
Checklist:
 2025.findings-emnlp.597.checklist.pdf