token-gating

Tag

Cards List
#token-gating

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

arXiv cs.LG · 2026-07-08 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