🔬 Research Summary by Dr Qinghua Lu, the team leader of the responsible AI science team at CSIRO's Data61. [Original paper by Qinghua Lu, Liming Zhu, Xiwei Xu, Zhenchang Xing, Jon Whittle] Overview: … [Read more...] about Towards Responsible AI in the Era of ChatGPT: A Reference Architecture for Designing Foundation Model based AI Systems
Research Summaries
Democratising AI: Multiple Meanings, Goals, and Methods
🔬 Research Summary by Elizabeth Seger, PhD, a researcher at the Centre for the Governance of AI (GovAI) in Oxford, UK, investigating beneficial AI model-sharing norms and practices. [Original paper by Elizabeth … [Read more...] about Democratising AI: Multiple Meanings, Goals, and Methods
System Safety and Artificial Intelligence
🔬 Research Summary by Roel Dobbe, an Assistant Professor working at the intersection of engineering, design and governance of data-driven and algorithmic control and decision-making systems. [Original paper by … [Read more...] about System Safety and Artificial Intelligence
A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning
🔬 Research Summary by Siobhan Mackenzie Hall, PhD student at the Oxford Neural Interfacing groups at the University of Oxford. Siobhan is also a member of the Oxford Artificial Intelligence Society, along with the … [Read more...] about A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning
A Hazard Analysis Framework for Code Synthesis Large Language Models
🔬 Research Summary by Heidy Khlaaf, an Engineering Director at Trail of Bits specializing in the evaluation, specification, and verification of complex or autonomous software implementations in safety-critical systems, … [Read more...] about A Hazard Analysis Framework for Code Synthesis Large Language Models