The 60-second answer
Token embeddings are learned lookup/representation vectors used internally as part of sequence modeling; retrieval embeddings are trained/pool representations to make semantic similarity meaningful under a chosen distance metric. Retrieval encoders need objectives with positives/negatives and often normalize vectors for cosine/dot-product ANN search.
Build the answer in this order
Token embeddings are learned lookup/representation vectors used internally as part of sequence modeling; retrieval embeddings are trained/pool representations to make semantic similarity meaningful under a chosen distance metric.
Retrieval encoders need objectives with positives/negatives and often normalize vectors for cosine/dot-product ANN search.
Evaluate retrieval embeddings by recall@K/MRR and hard-negative behavior, not by inspecting token-vector neighborhoods alone.
Consider chunk/document pooling, dimensionality, domain adaptation, index refresh, and embedding-version compatibility.
A useful interview mental model
This is the shape of a strong answer—not a script to memorize.
Senior-level signal
- Senior answers discuss representation anisotropy, hard-negative mining, and index/model version migration.
- Explain why generative next-token training does not automatically yield optimal sentence/document retrieval geometry.
What the interviewer is really testing
Likely follow-up questions
Common weak-answer patterns
- Reciting a definition without mechanism or assumptions.
- Claiming one technique is always better without a data regime.
- Stopping before failure modes, validation, or deployment implications.