This is joint work with Sahar Abdelnabi and David Krueger. It is mostly a linkpost for the paper (https://arxiv.org/abs/2609.36316) but also contains some additional commentary on CoT monitorability. TL;DR: Verbalization training makes a model less reticent about verbalizing a belief it already holds. We apply it to evaluation awareness and...
TL;DR * Models fine-tuned on synthetic documents describing what evaluations typically look like (e.g., multiple-choice questions, harmful requests, placeholders, conflicting goals) score safer on safety benchmarks. * This can happen in production-ready LLMs. Training on papers about AI benchmarks can create parametric knowledge about the structure of evaluations, which we...
This post is based on our paper Linear Control of Test Awareness Reveals Differential Compliance in Reasoning Models by Sahar Abdelnabi and Ahmed Salem from Microsoft. The Hawthorne Effect for AI You may have heard of the Hawthorne effect—the phenomenon where people change their behavior when they know they're being...