A single middle transformer layer trained in isolation recovers most RL post-training gains in LLMs, with gains concentrated in middle layers across models, algorithms, and tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training
A single middle transformer layer trained in isolation recovers most RL post-training gains in LLMs, with gains concentrated in middle layers across models, algorithms, and tasks.