5 citations · 7 across the 7 of their papers we have counts for
7 papers
Verification methods for international AI agreements
Akash R. Wasil, Tom Reed, Jack William Miller +1
What techniques can be used to verify compliance with international agreements about advanced AI development? In this paper, we examine 10 verification methods that could detect tw…
Measuring Sharpness in Grokking
Jack Miller, Patrick Gleeson, Charles O'Neill +2
Neural networks sometimes exhibit grokking, a phenomenon where perfect or near-perfect performance is achieved on a validation set well after the same performance has been obtained…
Grokking Beyond Neural Networks: An Empirical Exploration with Model Complexity
Jack Miller, Charles O'Neill, Thang Bui
In some settings neural networks exhibit a phenomenon known as \textit{grokking}, where they achieve perfect or near-perfect accuracy on the validation set long after the same perf…
AstroLLaMA: Towards Specialized Foundation Models in Astronomy
Tuan Dung Nguyen, Yuan-Sen Ting, Ioana Ciucă +21
Large language models excel in many human-language tasks but often falter in highly specialized domains like scholarly astronomy. To bridge this gap, we introduce AstroLLaMA, a 7-b…
Adversarial Fine-Tuning of Language Models: An Iterative Optimisation Approach for the Generation and Detection of Problematic Content
Charles O'Neill, Jack Miller, Ioana Ciuca +2
In this paper, we tackle the emerging challenge of unintended harmful content generation in Large Language Models (LLMs) with a novel dual-stage optimisation technique using advers…
Steering Language Generation: Harnessing Contrastive Expert Guidance and Negative Prompting for Coherent and Diverse Synthetic Data Generation
Charles O'Neill, Yuan-Sen Ting, Ioana Ciuca +2
Large Language Models (LLMs) hold immense potential to generate synthetic data of high quality and utility, which has numerous applications from downstream model training to practi…
Eigenvalue initialisation and regularisation for Koopman autoencoders
Jack W. Miller, Charles O'Neill, Navid C. Constantinou +1
Regularising the parameter matrices of neural networks is ubiquitous in training deep models. Typical regularisation approaches suggest initialising weights using small random valu…