3 papers
cs.CL2025
Evaluating Metrics for Safety with LLM-as-Judges
Kester Clegg, Richard Hawkins, Ibrahim Habli +1
LLMs (Large Language Models) are increasingly used in text processing pipelines to intelligently respond to a variety of inputs and generation tasks. This raises the possibility of…
cs.CY2025
The BIG Argument for AI Safety Cases
Ibrahim Habli, Richard Hawkins, Colin Paterson +4
We present our Balanced, Integrated and Grounded (BIG) argument for assuring the safety of AI systems. The BIG argument adopts a whole-system approach to constructing a safety case…
cs.LG2024
Learning Run-time Safety Monitors for Machine Learning Components
Ozan Vardal, Richard Hawkins, Colin Paterson +4
For machine learning components used as part of autonomous systems (AS) in carrying out critical tasks it is crucial that assurance of the models can be maintained in the face of p…