On Teacher Hacking in Language Model Distillation
Paper
•
2502.02671
•
Published
•
6
•
2
Daniil Tiapkin
dtiapkin
·
AI & ML interests
Reinforcement learning enjoyer
Recent Activity
upvoted
a
paper
1 day ago
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language
Model
upvoted
a
paper
1 day ago
On Teacher Hacking in Language Model Distillation
authored
a paper
1 day ago
Demonstration-Regularized RL
Organizations
None yet
dtiapkin's activity
commented
a
paper
1 day ago