collaborators

6 papers

cs.LG2026

Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation

Helena Casademunt, Bartosz Cywiński, Khoi Tran +3

Large language models sometimes produce false or misleading responses. Two approaches to this problem are honesty elicitation -- modifying prompts or weights so that the model answ…

cs.CV2026

Precise Parameter Localization for Textual Generation in Diffusion Models

Łukasz Staniszewski, Bartosz Cywiński, Franziska Boenisch +2

Novel diffusion models can synthesize photo-realistic images with integrated high-quality text. Surprisingly, we demonstrate through attention activation patching that only less th…

cs.LG2026

Simple LLM Baselines are Competitive for Model Diffing

Elias Kempf, Simon Schrodi, Bartosz Cywiński +3

Standard LLM evaluations only test capabilities or dispositions that evaluators designed them for, missing unexpected differences such as behavioral shifts between model revisions…

cs.LG2025

Eliciting Secret Knowledge from Language Models

Bartosz Cywiński, Emil Ryd, Rowan Wang +4

We study secret elicitation: discovering knowledge that an AI possesses but does not explicitly verbalize. As a testbed, we train three families of large language models (LLMs) to…

cs.LG2025

SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders

Bartosz Cywiński, Kamil Deja

Diffusion models, while powerful, can inadvertently generate harmful or undesirable content, raising significant ethical and safety concerns. Recent machine unlearning approaches o…

cs.LG2025

Towards eliciting latent knowledge from LLMs with mechanistic interpretability

Bartosz Cywiński, Emil Ryd, Senthooran Rajamanoharan +1

As language models become more powerful and sophisticated, it is crucial that they remain trustworthy and reliable. There is concerning preliminary evidence that models may attempt…