95 citations · 122 across the 16 of their papers we have counts for
17 papers
Training LLMs to Verbalize Evaluation Awareness
Usman Anwar, Sahar Abdelnabi, David Krueger
Evaluation awareness (EA) can cause large language models (LLMs) to behave differently during audits than in deployment, yet measuring and accounting for EA remains challenging. We…
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…
A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring
Usman Anwar, Julianna Piskorz, David D. Baek +6
Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanisms. Yet principled methods to de…
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…
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…
The Reality of AI and Biorisk
Aidan Peppin, Anka Reuel, Stephen Casper +10
To accurately and confidently answer the question 'could an AI model or system increase biorisk', it is necessary to have both a sound theoretical threat model for how AI models or…
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.…
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…
Noisy Zero-Shot Coordination: Breaking The Common Knowledge Assumption In Zero-Shot Coordination Games
Usman Anwar, Ashish Pandian, Jia Wan +2
Zero-shot coordination (ZSC) is a popular setting for studying the ability of reinforcement learning (RL) agents to coordinate with novel partners. Prior ZSC formulations assume th…
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…
IDs for AI Systems
Alan Chan, Noam Kolt, Peter Wills +7
AI systems are increasingly pervasive, yet information needed to decide whether and how to engage with them may not exist or be accessible. A user may not be able to verify whether…
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
Usman Anwar, Abulhair Saparov, Javier Rando +39
This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are organized into three different categories…
Reward Model Ensembles Help Mitigate Overoptimization
Thomas Coste, Usman Anwar, Robert Kirk +1
Reinforcement learning from human feedback (RLHF) is a standard approach for fine-tuning large language models to follow instructions. As part of this process, learned reward model…
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Stephen Casper, Xander Davies, Claudia Shi +29
Reinforcement learning from human feedback (RLHF) is a technique for training AI systems to align with human goals. RLHF has emerged as the central method used to finetune state-of…
Domain Generalization for Robust Model-Based Offline Reinforcement Learning
Alan Clark, Shoaib Ahmed Siddiqui, Robert Kirk +3
Existing offline reinforcement learning (RL) algorithms typically assume that training data is either: 1) generated by a known policy, or 2) of entirely unknown origin. We consider…
Inverse Constrained Reinforcement Learning
Usman Anwar, Shehryar Malik, Alireza Aghasi +1
In real world settings, numerous constraints are present which are hard to specify mathematically. However, for the real world deployment of reinforcement learning (RL), it is crit…
Learning To Solve Differential Equations Across Initial Conditions
Shehryar Malik, Usman Anwar, Ali Ahmed +1
Recently, there has been a lot of interest in using neural networks for solving partial differential equations. A number of neural network-based partial differential equation solve…