specific method · filed under post-training
Reinforcement Learning from Human Feedback
A reinforcement-learning approach used to refine conversational quality and align model behavior using human feedback.
Also called RLHF.
- sources
- 3
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 3
Documented in
Further reading
Picked by hand, not extracted: where to read more, not evidence for anything on this page.
- Training language models to follow instructions with human feedback (Ouyang et al., 2022) paper arxiv.orgInstructGPT; canonical LLM RLHF pipeline
Evidence
3 spans quoted from the sources, strongest treatment first.
Conversational quality was further refined through RLHF
usedoptimizationin Nemotron 3 UltraNVIDIA
Nemotron 3 Ultra 550B-A55B GenRM: GenRM used for RLHF
usedpost trainingin Nemotron 3 UltraNVIDIA
Chat teacher training involves multiple RLHF iterations
usedoptimizationin Nemotron 3 Ultra (Chat teacher)NVIDIA
Filed alongside
Other methods under post-training :: preference optimization.