18 citations · 44 across the 10 of their papers we have counts for
13 papers
User Model Extraction via Belief Self-Distillation
Ali Holmov, Yiran Huang, Kirill Bykov +1
Large language models (LLMs) implicitly infer attributes of their users and adapt their behavior accordingly, yet these beliefs remain difficult to inspect and causally manipulate.…
Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas
Nils A. Herrmann, Leander Girrbach, Kirill Bykov +1
Recent work shows that large language models (LLMs) encode behavioral traits ("personas") as linear directions in activation space, often called "persona vectors". Prior work has u…
Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
Laura Kopf, Nils Feldhus, Kirill Bykov +4
Automated interpretability research aims to identify concepts encoded in neural network features to enhance human understanding of model behavior. Within the context of large langu…
Deep Learning Meets Teleconnections: Improving S2S Predictions for European Winter Weather
Philine L. Bommer, Marlene Kretschmer, Fiona R. Spuler +2
Predictions on subseasonal-to-seasonal (S2S) timescales--ranging from two weeks to two month--are crucial for early warning systems but remain challenging owing to chaos in the cli…
CoSy: Evaluating Textual Explanations of Neurons
Laura Kopf, Philine Lou Bommer, Anna Hedström +3
A crucial aspect of understanding the complex nature of Deep Neural Networks (DNNs) is the ability to explain learned concepts within their latent representations. While methods ex…
Manipulating Feature Visualizations with Gradient Slingshots
Dilyara Bareeva, Marina M. -C. Höhne, Alexander Warnecke +5
Feature Visualization (FV) is a widely used technique for interpreting concepts learned by Deep Neural Networks (DNNs), which synthesizes input patterns that maximally activate a g…
Labeling Neural Representations with Inverse Recognition
Kirill Bykov, Laura Kopf, Shinichi Nakajima +2
Deep Neural Networks (DNNs) demonstrate remarkable capabilities in learning complex hierarchical data representations, but the nature of these representations remains largely unkno…
Mark My Words: Dangers of Watermarked Images in ImageNet
Kirill Bykov, Klaus-Robert Müller, Marina M. -C. Höhne
The utilization of pre-trained networks, especially those trained on ImageNet, has become a common practice in Computer Vision. However, prior research has indicated that a signifi…
DORA: Exploring Outlier Representations in Deep Neural Networks
Kirill Bykov, Mayukh Deb, Dennis Grinwald +2
Deep Neural Networks (DNNs) excel at learning complex abstractions within their internal representations. However, the concepts they learn remain opaque, a problem that becomes par…
Visualizing the Diversity of Representations Learned by Bayesian Neural Networks
Dennis Grinwald, Kirill Bykov, Shinichi Nakajima +1
Explainable Artificial Intelligence (XAI) aims to make learning machines less opaque, and offers researchers and practitioners various tools to reveal the decision-making strategie…
Explaining Bayesian Neural Networks
Kirill Bykov, Marina M. -C. Höhne, Adelaida Creosteanu +4
To advance the transparency of learning machines such as Deep Neural Networks (DNNs), the field of Explainable AI (XAI) was established to provide interpretations of DNNs' predicti…
NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weights
Kirill Bykov, Anna Hedström, Shinichi Nakajima +1
Many efforts have been made for revealing the decision-making process of black-box learning machines such as deep neural networks, resulting in useful local and global explanation…
How Much Can I Trust You? -- Quantifying Uncertainties in Explaining Neural Networks
Kirill Bykov, Marina M. -C. Höhne, Klaus-Robert Müller +2
Explainable AI (XAI) aims to provide interpretations for predictions made by learning machines, such as deep neural networks, in order to make the machines more transparent for the…