token-gating

Tag

Cards List
#token-gating

A Coin Flip Per Token: Bernoulli Sparse Steering of Large Language Models

arXiv cs.LG · 19h ago Cached

Introduces Stochastic Token Steering (STS) and Stochastic Block Steering (SBS) for LLM activation steering, which probabilistically gate steering signals per token or per sequence. Shows that steering only 50% of tokens recovers most of the dense-steering effect while preserving fluency, and that the behavioral outcome is rate-limited by cumulative signal dosage.

0 favorites 0 likes
← Back to home

Submit Feedback