activity
20242026
collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory

Usman Anwar, Tim Bakker, Dana Kianfar +2

Chain-of-thought (CoT) monitors are LLM-based systems that analyze reasoning traces to detect when outputs may exhibit attributes of interest, such as test-hacking behavior during…

cs.LG2025

Understanding In-Context Learning of Linear Models in Transformers Through an Adversarial Lens

Usman Anwar, Johannes Von Oswald, Louis Kirsch +2

In this work, we make two contributions towards understanding of in-context learning of linear models by transformers. First, we investigate the adversarial robustness of in-contex…

cs.LG2025

Mitigating Goal Misgeneralization via Minimax Regret

Karim Abdel Sadek, Matthew Farrugia-Roberts, Usman Anwar +4

Safe generalization in reinforcement learning requires not only that a learned policy acts capably in new situations, but also that it uses its capabilities towards the pursuit of…

cs.LG2025

Interpreting Emergent Planning in Model-Free Reinforcement Learning

Thomas Bush, Stephen Chung, Usman Anwar +2

We present the first mechanistic evidence that model-free reinforcement learning agents can learn to plan. This is achieved by applying a methodology based on concept-based interpr…

cs.LG2024

Learning to Forget using Hypernetworks

Jose Miguel Lara Rangel, Stefan Schoepf, Jack Foster +2

Machine unlearning is gaining increasing attention as a way to remove adversarial data poisoning attacks from already trained models and to comply with privacy and AI regulations.…

cs.LG2024

Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks

Madeline Brumley, Joe Kwon, David Krueger +2

A key objective of interpretability research on large language models (LLMs) is to develop methods for robustly steering models toward desired behaviors. To this end, two distinct…