SFT on LLMs removes noise-like token interactions in a brief early phase before introducing overfitted ones, explaining inconsistent effectiveness across model scales.
Ma-rlhf: Rein- forcement learning from human feedback with macro actions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Reconciling Contradictory Views on the Effectiveness of SFT in LLMs: An Interaction Perspective
SFT on LLMs removes noise-like token interactions in a brief early phase before introducing overfitted ones, explaining inconsistent effectiveness across model scales.