implementation detail · not yet filed
masking-based refinement
Also called mask fine-tuning.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
mask fine-tuning, allowing knowledge acquired during reinforcement learning to be injected back
usedpost trainingin GLM-5Z.ai