Do embeddings need manually labeled examples?
Not always. Token prediction can use text itself to supply targets, while other objectives use labeled pairs, interaction data, or automatically constructed examples.
Explore This Question
Search for additional explanations using these tools:
More FAQs in How are embeddings learned during model training?
No. An implementation can freeze an embedding layer while training other parameters. Whether embeddings change depends on which parameters the optimizer is allowed to update.
A new model can produce a different vector space. Query vectors and stored document vectors may no longer be compatible unless the collection is re-encoded consistently.
Still have questions?
Browse all our FAQs or reach out to our support team