AlphaToken decouples adaptation and stability into path-aware token valuations for LLM post-training using a Fisher-drift proxy to mask low-value tokens and improve performance while reducing catastrophic forgetting.
arXiv preprint arXiv:2509.23873 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training
AlphaToken decouples adaptation and stability into path-aware token valuations for LLM post-training using a Fisher-drift proxy to mask low-value tokens and improve performance while reducing catastrophic forgetting.