AI engineering glossary · LLM training alignment
What is chosen and rejected responses?
Chosen and rejected responses (also called Winner and loser responses): The two answers stored in a preference example: the chosen (preferred) response and the rejected (dispreferred) one. Preference training pushes the model to make the chosen answer more likely than the rejected answer for the same prompt.
Chosen and rejected responses: an example
For the prompt 'Is it safe to share my OTP?', the chosen response says never share it and the rejected one says it is fine with a bank employee.
Related terms
More LLM training alignment terms
- Clipped surrogate objective
- Common Crawl
- Compute-optimal training
- Constitutional AI
- Continued pretraining
- Critical batch size
- Data curation
- Data mixture
Where you learn it
Chosen and rejected responses is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.