Retrieval and search · MLD-0117
Bi-encoder
Encoding queries and candidates separately so their vectors can be compared efficiently.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Precompute document embeddings for search.
Original caveat
Separate encoding limits direct token-level query-document interaction.
Context and aliases
Level: Intermediate. Stages: Data · Retrieval · Inference · Evaluation.
Tags: ML · NLP · SLM · LLM · IR.
Aliases: Dual encoder · two-tower encoder.
Related concepts
Concepts linking here
Original references
- Faiss documentation ↗ · Reference link
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks ↗ · Consulted
- Sentence Transformers documentation ↗ · Reference link
- Original reference URL ↗