Hypothetical Document Embeddings
Also called HyDE.
Hypothetical Document Embeddings (HyDE) improves retrieval by having a model write a hypothetical answer to the query, embedding that answer, and searching for real documents similar to it.
Description
The generated document may contain errors, but its embedding tends to lie closer to relevant real documents than the short query does.
Sources
- Gao et al. (2022). Precise Zero-Shot Dense Retrieval without Relevance Labels.
Cite this entry
Protologue. (2026). Hypothetical Document Embeddings. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0056). https://protologue.com/t/hypothetical-document-embeddings/
BibTeX
@misc{protologue_hypothetical_document_embeddings,
title = {Hypothetical Document Embeddings},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0056},
url = {https://protologue.com/t/hypothetical-document-embeddings/}
}