stapo-spurious-token-silencing

【效率与协作】Stabilize RL training in LLMs by detecting and masking gradient contributions from spurious tokens that comprise 0.01% of output but cause disproportionate instability. Identifies tokens with low probability, low entropy, and positive advantage, then suppresses their gradients during optimization to maintain stable policy entropy and improve reasonin…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准