AI Paper Atlas

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

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets

Jack Hopkins, Dipika Khullar, Fabien Roger

ICML 2026 · Large language models › Language, safety and interpretability · approach: Reasoning mechanisms and failure modes · 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
Amplify reasoning task vector beyond alpha=1 (uniform) (ablation)Qwen3-VL reasoning model · Secret Word (Taboo) 8Baudit success rate: 3.1% -> 8.6%Improved
Amplify reasoning task vector to alpha=1.5 (uniform) (ablation)Qwen3-VL-8B · Secret Belief (Gender)audit success rate: 3.1% -> 17.2%Improved
Amplify reasoning task vector to alpha=3.0 (uniform) (ablation)Qwen3-VL-32B · Secret Behavior (SSC)audit success rate: 0.0% -> 5.5%Improved
Amplify to high alpha (4.0) uniform (ablation)Qwen3-VL-8B · Secret Belief (Gender)audit success rate: 17.2% -> 0.8%Hurt
Amplify in-context secret setting (ablation)Qwen3-VL-8B · In-Context Secret (MMLU)audit success rate: 1.2% -> 2.3%Mixed
Use best layer-wise coefficient method instead of uniform (ablation)Overthinking, Qwen3-VL-8B · Secret Word (Taboo)audit success rate: 6.3% -> 25.5% at alpha=2Improved
Use best layer-wise coefficient method instead of uniform (ablation)Overthinking, Qwen3-VL-32B · Secret Behavior (SSC)audit success rate: 2.3% -> 18.8% at alpha=2.5Improved
Add metacognitive prefill to overthinking (best) (ablation)Overthinking, Qwen3-VL-32B · Secret Behavior (SSC)audit success rate: 18.8% -> 52.9% at alpha=2.5Improved
Add prefill to overthinking (best) (ablation)Overthinking, Qwen3-VL-8B · Secret Belief (Gender)audit success rate: 23.4% -> 95.7% at alpha=1.5Improved
Add direct prefill to overthinking (best) (ablation)Overthinking, Qwen3-VL-8B · Secret Word (Taboo)audit success rate: 25.5% -> 9.4%Hurt
Add overthinking on top of prefill (ablation)Prefill attack, Qwen3-VL-8B · In-Context Secret (MMLU)audit success rate: 39.8% -> 30.6%Hurt
Replace task vector direction with random perturbation of equal magnitude (ablation)Overthinking · Secret Behavior (SSC)audit success rateHurt

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