9 papers
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…
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…
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…
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…
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-…
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,…