collaborators

5 papers

cs.LG2026

Removing Sandbagging in LLMs by Training with Weak Supervision

Emil Ryd, Henning Bartsch, Julian Stastny +2

As AI systems begin to automate complex tasks, supervision increasingly relies on weaker models or limited human oversight that cannot fully verify output quality. A model more cap…

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

Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment

Nevan Wichers, Aram Ebtekar, Ariana Azarbal +8

Large language models are sometimes trained with imperfect oversight signals, leading to undesired behaviors such as reward hacking and sycophancy. Improving oversight quality can…

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…

cs.LG2025

Fine Flood Forecasts: Incorporating local data into global models through fine-tuning

Emil Ryd, Grey Nearing

Floods are the most common form of natural disaster and accurate flood forecasting is essential for early warning systems. Previous work has shown that machine learning (ML) models…