1 citations · 1 across the 7 of their papers we have counts for
9 papers
LLM Agents Can Easily Tamper With Their Own Traces
Jeremy Qin, David Schmotz, Derck Prinzhorn +3
Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents cannot ta…
Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure
David Schmotz, Derck Prinzhorn, Luca Beurer-Kellner +3
A central concern in AI safety is that agents may treat oversight as an obstacle when it conflicts with completing their goals. We study instrumental evasion, the propensity of LLM…
Measuring AI Accountability Through Argumentation Analysis: Can Model Reasoning Withstand Scrutiny?
Daan R. Henselmans, Derck W. E. Prinzhorn, Arno Libert
AI oversight methods rely on ground truth for validation, but what constitutes appropriate AI behavior is contested. This leaves evaluation of moral reasoning in LLMs and debate-ba…
Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment
Arno Libert, Derck W. E. Prinzhorn, Daan R. Henselmans
AI alignment requires AI systems to adhere to human norms, values, or intentions. Under value pluralism there is no correct target, but a shared prerequisite is that the system's b…
ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D
Lena Libon, Ben Rank, Jehyeok Yeon +5
As AI agents begin to automate AI R&D, we need ways to assess whether their outputs are safe to deploy, even when the agents themselves may be untrusted. AI control offers one such…
Injecting Image Guidance into Text-Conditioned Diffusion Models at Inference
Agata Żywot, Iason Skylitsis, Thijmen Nijdam +4
Text-to-image diffusion models like Stable Diffusion generate high-quality images from text, but lack a way to inject visual guidance (e.g. sketches, styles) at inference without r…
Evaluating Newtonian Mechanics in Video Generative Models with Real Physical Systems
Antonios Tragoudaras, Chenyu Zhang, Daniil Cherniavskii +7
Recent advances in image and video generation raise hopes that these models possess world modeling capabilities-the ability to generate realistic, physically plausible videos. This…
Conformal time series decomposition with component-wise exchangeability
Derck W. E. Prinzhorn, Thijmen Nijdam, Putri A. van der Linden +1
Conformal prediction offers a practical framework for distribution-free uncertainty quantification, providing finite-sample coverage guarantees under relatively mild assumptions on…
Reproducibility study of FairAC
Gijs de Jong, Macha J. Meijer, Derck W. E. Prinzhorn +1
This work aims to reproduce the findings of the paper "Fair Attribute Completion on Graph with Missing Attributes" written by Guo, Chu, and Li arXiv:2302.12977 by investigating the…