4 papers
Chain of Thought Monitoring Can Fail Even When CoT Is Necessary
Lennart Bürger, Piotr Komorowski, Moritz Weckbecker +4
Chain of Thought (CoT) monitoring is used by frontier labs to detect misbehaviour of AI systems. Yet, its reliability remains poorly understood. We attribute this to the lack of a…
Predicting Future Behaviors in Reasoning Models Enables Better Steering
Evgenii Kortukov, Piotr Komorowski, Florian Klein +5
Deployed large reasoning models (LRMs) often behave unexpectedly. Test-time steering controls LRM outputs by intervening on their hidden representations, but it can degrade output…
Towards Visually Explaining Statistical Tests with Applications in Biomedical Imaging
Masoumeh Javanbakhat, Piotr Komorowski, Dilyara Bareeva +3
Deep neural two-sample tests have recently shown strong power for detecting distributional differences between groups, yet their black-box nature limits interpretability and practi…
Attribution-Guided Decoding
Piotr Komorowski, Elena Golimblevskaia, Reduan Achtibat +3
The capacity of Large Language Models (LLMs) to follow complex instructions and generate factually accurate text is critical for their real-world application. However, standard dec…