// ⌕ RAG & Vector Retrieval
HyDE (Hypothetical Document Embeddings)
Generate a hypothetical answer, then retrieve real documents with it.
HyDE 假设文档检索 2022 Foundational extended
IN PLAIN WORDS
Questions and answers are phrased differently. An LLM writes a (possibly wrong) hypothetical document whose embedding retrieves real ones better, with no labeled data.
Used in: Query rewriting in RAG
TIMELINE · prerequisites → this → what builds on it
01Original paper
Precise Zero-Shot Dense Retrieval without Relevance Labels
Luyu Gao, Xueguang Ma, Jimmy Lin, et al. · 2022
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Then you can learn
- Nothing in the atlas builds on it yet
Related:GraphRAG
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
04Where the course teaches it
On learning paths:AI Application Engineer
For AI / data
- Verification: verified, checked 2026-10-22.
- JSON: /api/learn/algorithms.json (id:
hyde)