AI engineering glossary · LLM training alignment
What is ultraFeedback?
UltraFeedback: A large open preference dataset in which many prompts have several model-generated responses scored by a strong model on criteria like helpfulness and honesty, widely used to train open reward models and DPO-tuned chat models.
UltraFeedback: an example
Its scored response pairs are converted to chosen and rejected pairs for DPO training.
Related terms
More LLM training alignment terms
- Value function
- Warmup-stable-decay schedule
- Weak-to-strong generalisation
- ZeRO
- 3D parallelism
- 8-bit optimiser
- Adapter
- Advantage function
Where you learn it
UltraFeedback is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.