works on
activation steering 1evaluation awareness 1large language models 1model safety 1prompt optimization 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.LG2026

Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models

Deepanshu Mody, Samarth Agarwal, Utkarsh Mittal +1

The paper investigates how to suppress specific internal activations in large language models by optimizing only the input prompt, aiming to hide evaluation-awareness signals witho…