AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering

Eric Bigelow, Daniel Wurgaft, YingQiao Wang, Noah Goodman, Tomer Ullman, Hidenori Tanaka, Ekdeep Singh Lubana

ICML 2026 · Large language models › Language, safety and interpretability · approach: Mechanistic analysis of attention and representations · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase number of in-context shotsLlama-3.1-8B-Instruct · persona datasetspersona-matching behaviorImproved
apply positive activation steering magnitudeLlama-3.1-8B-Instruct · persona datasetspersona-matching behaviorImproved
apply negative activation steering magnitudeLlama-3.1-8B-Instruct · persona datasetspersona-matching behaviorHurt
increase steering magnitude beyond the monotone rangeLlama-3.1-8B-Instruct · persona datasetsbehaviorHurt
steer with vectors computed over multiple shots instead of a single query (ablation)CAA steering · persona datasetssteering effectHurt
apply CAA steering to phi-4-mini-instructphi-4-mini-instruct · persona datasetsbehaviorNo clear effect
steer at layers other than one or a few layersLlama-3.1-8B-Instruct · persona datasetsbehaviorNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy