works on

From the 1 of 6 linked papers with an AI index.

collaborators

6 papers

cs.LG2026

Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values

Jan Betley, Johannes Treutlein, Jan Dubiński +7

The paper identifies and measures covert value leakage, where large language models let their own values subtly bias answers without informing users, and introduces evaluation suit…

cs.CL2026

Negation Neglect: When models fail to learn negations in training

Harry Mayne, Lev McKinney, Jan Dubiński +3

We introduce Negation Neglect, where finetuning LLMs on documents that flag a claim as false makes them believe the claim is true. For example, models are finetuned on documents th…

cs.CV2026

Jailbreaking Vision-Language Models Through the Visual Modality

Aharon Azulay, Jan Dubiński, Zhuoyun Li +2

The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision co…

cs.LG2026

Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers

Jan Dubiński, Jan Betley, Anna Sztyber-Betley +2

Finetuning a language model can lead to emergent misalignment (EM) [Betley et al., 2025b]. Models trained on a narrow distribution of misaligned behavior generalize to more egregio…

cs.CV2026

Conditioned Activation Transport for T2I Safety Steering

Maciej ChrabÄ szcz, Aleksander Szymczyk, Jan Dubiński +3

Despite their impressive capabilities, current Text-to-Image (T2I) models remain prone to generating unsafe and toxic content. While activation steering offers a promising inferenc…

cs.LG2025

Learning Graph Representation of Agent Diffusers

Youcef Djenouri, Nassim Belmecheri, Tomasz Michalak +3

Diffusion-based generative models have significantly advanced text-to-image synthesis, demonstrating impressive text comprehension and zero-shot generalization. These models refine…