About the project
This PhD project aims to delve into the intricacies of deep learning-based systems, focusing on developing comprehensive verification techniques to ascertain their behaviour and output. The project is motivated by the increasing reliance on learning-enabled systems in critical decision-making processes and the need to ensure that these models are not only accurate but also reliable and trustworthy.
The emergence of Large Language Models (LLMs) is now transforming the landscape of Natural Language Processing (NLP) and multimodal applications as we speak. However, LLMs such as GPT-4 and its applications such as ChatGPT come with health warnings and easy to break guardrails. The need for reliable LLM verification techniques is now critical.
This project’s outcomes will play a crucial role in advancing our understanding of LLMs and how to better verify and validate them, researching the necessary tools to ensure their robustness and reliability and creating a pathway to ultimately fostering trust in the AI applications that use them (e.g. chatbots, question answer systems, decision support systems, robotics and automation systems).
We're also looking for candidates with expertise beyond NLP and LLMs, including Trustworthy AI, Robotics, Game Theory, Energy Systems, and Control, especially with deep learning experience.
Prospective candidates are invited to apply soon, as we will be reviewing applications on a rolling basis. Successful candidates would have a strong background in Computer Sciences, Engineering, Maths or Physics and preference would be given to those with good understanding of Deep Learning models.
You will join the School of Electronics and Computer Science, ranked 1st in the UK for Electrical and Electronic Engineering within the University of Southampton, ranked top 1% of universities worldwide. We will also support the development of your future career and give you opportunities including teaching assistantships, professional networking via leading organizations such as Alan Turing Institute, £31M RAI UK Hub, and access to Future Worlds to explore commercialization of your research.
