Mid-layer LLM value vectors, projected through a contrastively trained MLP, enable zero-shot retrieval of documents by ad-hoc entity type.
In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6769–6781, Online
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings
Mid-layer LLM value vectors, projected through a contrastively trained MLP, enable zero-shot retrieval of documents by ad-hoc entity type.