SLASH is a plug-and-play attention redistribution technique that counters attention sinks to enhance LLMs' intrinsic graph topology reconstruction without any training or fine-tuning.
The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Activation steering is cast as constrained optimization that minimizes collateral damage by weighting perturbations according to the empirical second-moment matrix of activations instead of assuming isotropy.
citing papers explorer
-
SLASH the Sink: Sharpening Structural Attention Inside LLMs
SLASH is a plug-and-play attention redistribution technique that counters attention sinks to enhance LLMs' intrinsic graph topology reconstruction without any training or fine-tuning.
-
Minimizing Collateral Damage in Activation Steering
Activation steering is cast as constrained optimization that minimizes collateral damage by weighting perturbations according to the empirical second-moment matrix of activations instead of assuming isotropy.