Unifying LLM Control: A Bayesian Framework for ICL and Activation Steering

dl_weekly · x · 2026-07-30

Recommends a paper exploring inference-time control methods for LLMs titled 'Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering'.

The paper proposes a unifying, predictive account of model behavior control from a Bayesian perspective:

The proposed closed-form Bayesian model explains prior empirical phenomena (e.g., sigmoidal learning curves) and predicts novel ones, such as the additivity of both interventions in log-belief space, which can induce sudden behavioral shifts from slight changes.

Original post →

More from Research

Research channel →