Ewart, Aidan

Eight Methods to Evaluate Robust Unlearning in LLMs

Lynch, A., Guo, P., Ewart, A., Casper, S., & Hadfield-Menell, D. (2024) · arXiv

Privacy-Preserving Technologies in DataAdversarial Robustness in Machine Learning

Cited by 188

Sparse Autoencoders Find Highly Interpretable Features in Language Models

Cunningham, H., Ewart, A., Riggs, L., Huben, R., & Sharkey, L. (2023) · arXiv

Explainable Artificial Intelligence (XAI)Topic Modeling

Cited by 61

Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Sheshadri, A., Ewart, A., Guo, P., Lynch, A., Wu, C., Hebbar, V., Sleight, H., Stickland, A. C., Perez, E., Hadfield-Menell, D., et al. (2024) · arXiv

Adversarial Robustness in Machine LearningPrivacy-Preserving Technologies in Data

Cited by 3