8 papers
Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models
Dewi Gould, Francis Rhys Ward, Anders Cairns Woodruff +18
Many efforts to ensure frontier AI models are safe rely on monitoring their chain-of-thought (CoT) reasoning. If models become able to perform sufficiently complex reasoning intern…
SKATE, a Scalable Tournament Eval: Weaker LLMs differentiate between stronger ones using verifiable challenges
Dewi S. W. Gould, Bruno Mlodozeniec, Samuel F. Brown
Evaluating the capabilities and risks of foundation models is paramount, yet current methods demand extensive domain expertise, hindering their scalability as these models rapidly…
A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior
Harry Mayne, Justin Singh Kang, Dewi Gould +3
LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process is poorly understood. Existing faithful…
A framework for assuring the accuracy and fidelity of an AI-enabled Digital Twin of en route UK airspace
Adam Keane, Nick Pepper, Chris Burr +4
Digital Twins combine simulation, operational data and Artificial Intelligence (AI), and have the potential to bring significant benefits across the aviation industry. Project Blue…
A Probabilistic Digital Twin of UK En Route Airspace for Training and Evaluating AI Agents for Air Traffic Control
Nick Pepper, Adam Keane, Amy Hodgkin +11
This paper presents the first probabilistic Digital Twin of operational en route airspace, developed for the London Area Control Centre. The Digital Twin is intended to support the…
PAC Apprenticeship Learning with Bayesian Active Inverse Reinforcement Learning
Ondrej Bajgar, Dewi S. W. Gould, Jonathon Liu +3
As AI systems become increasingly autonomous, reliably aligning their decision-making with human preferences is essential. Inverse reinforcement learning (IRL) offers a promising a…