144 citations · 335 across the 12 of their papers we have counts for
12 papers
SAE-StatSteer: Statistical Consensus Feature Selection for Optimization-Free Activation Steering of Large Language Models
Oshayer Siddique, J. M Areeb Uzair Alam, Md Jobayer Rahman Rafy +3
Activation steering adds a residual-stream direction at inference time, providing lightweight behavioral control without fine-tuning. Sparse autoencoders (SAEs) can make such inter…
Scaling Trends for Lie Detector Oversight in Preference Learning
Oskar J. Hollinsworth, Ann-Kathrin Dombrowski, Sam Adam-Day +2
Deceptive behavior in LLMs is costly to monitor and prevent, motivating approaches such as Scalable Oversight via Lie Detectors (SOLiD) (Cundy & Gleave, 2025), which uses lie detec…
The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models
Ann-Kathrin Dombrowski, Dillon Bowen, Adam Gleave +1
Open-weight large language models (LLMs) unlock huge benefits in innovation, personalization, privacy, and democratization. However, their core advantage - modifiability - opens th…
AI Companies Should Report Pre- and Post-Mitigation Safety Evaluations
Dillon Bowen, Ann-Kathrin Dombrowski, Adam Gleave +1
The rapid advancement of AI systems has raised widespread concerns about potential harms of frontier AI systems and the need for responsible evaluation and oversight. In this posit…
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Nathaniel Li, Alexander Pan, Anjali Gopal +54
The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and che…
Representation Engineering: A Top-Down Approach to AI Transparency
Andy Zou, Long Phan, Sarah Chen +18
In this paper, we identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights f…
Diffeomorphic Counterfactuals with Generative Models
Ann-Kathrin Dombrowski, Jan E. Gerken, Klaus-Robert Müller +1
Counterfactuals can explain classification decisions of neural networks in a human interpretable way. We propose a simple but effective method to generate such counterfactuals. Mor…
Automated Dissipation Control for Turbulence Simulation with Shell Models
Ann-Kathrin Dombrowski, Klaus-Robert Müller, Wolf Christian Müller
The application of machine learning (ML) techniques, especially neural networks, has seen tremendous success at processing images and language. This is because we often lack formal…
Towards Robust Explanations for Deep Neural Networks
Ann-Kathrin Dombrowski, Christopher J. Anders, Klaus-Robert Müller +1
Explanation methods shed light on the decision process of black-box classifiers such as deep neural networks. But their usefulness can be compromised because they are susceptible t…
Fairwashing Explanations with Off-Manifold Detergent
Christopher J. Anders, Plamen Pasliev, Ann-Kathrin Dombrowski +2
Explanation methods promise to make black-box classifiers more transparent. As a result, it is hoped that they can act as proof for a sensible, fair and trustworthy decision-making…
Explanations can be manipulated and geometry is to blame
Ann-Kathrin Dombrowski, Maximilian Alber, Christopher J. Anders +3
Explanation methods aim to make neural networks more trustworthy and interpretable. In this paper, we demonstrate a property of explanation methods which is disconcerting for both…
CNN Cascades for Segmenting Whole Slide Images of the Kidney
Michael Gadermayr, Ann-Kathrin Dombrowski, Barbara Mara Klinkhammer +2
Due to the increasing availability of whole slide scanners facilitating digitization of histopathological tissue, there is a strong demand for the development of computer based ima…