activity
20242026
collaborators

9 papers

cs.AI2026

Rule of Thumb: Explaining Artificial Intelligence Systems using Partial Information

Kaivalya Rawal, Daria Onitiu, Brent Mittelstadt +2

Explainable Artificial Intelligence (XAI) seeks to explain how an Artificial Intelligence (AI) system arrived at a particular decision. We propose ''Rule of Thumb'' (RoT) explanati…

cs.CL2026

The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning

Will Hawkins, Kaivalya Rawal, Jonathan Rystrøm +8

Fine-tuning a large language model is a ubiquitous method for enhancing its capability on a specific downstream task. However, prior work has shown that this increase in capability…

cs.CY2026

The Fallacy of Sustainable Generative AI: Limitations in EU Environmental Regulation of Data Centres and Paths Forward

Daria Onitiu, Sandra Wachter, Brent Mittelstadt

In the age of Artificial Intelligence (AI), Large Language Models, Generative AI and larger frontier AI models, data centres create a significant environmental burden on electricit…

cs.CY2026

AI-Mediated Communication Can Steer Collective Opinion

Stratis Tsirtsis, Kai Rawal, Chris Russell +2

Generative artificial intelligence (AI) is increasingly integrated into the online platforms where humans exchange opinions; large language models (LLMs) now polish users' posts on…

cs.CY2025

Deepfakes on Demand: the rise of accessible non-consensual deepfake image generators

Will Hawkins, Chris Russell, Brent Mittelstadt

Advances in multimodal machine learning have made text-to-image (T2I) models increasingly accessible and popular. However, T2I models introduce risks such as the generation of non-…

cs.AI2024

The effect of fine-tuning on language model toxicity

Will Hawkins, Brent Mittelstadt, Chris Russell

Fine-tuning language models has become increasingly popular following the proliferation of open models and improvements in cost-effective parameter efficient fine-tuning. However,…