EPSRC iCASE Studentship on Assuring Large Language Models Through Knowledge Graph Infusion


Funded PhD


4 years

Application deadline:

21 May 2024

About this project

Recently, Large Language Models (LLMs) have seen huge advancement. QinetiQ is developing an AI Assurance Framework, to allow such tools to be responsibly utilised by UK Defence and other government agencies. Assuring LLMs is a complex and rapidly evolving field, where trustworthiness and factuality are less well understood than more mature AI technologies.

This project aims to assure LLM products and improve their performance using Neuro-Symbolic AI. Research in Neuro-Symbolic AI focuses on combining neural network-based technologies (such as Deep Learning and LLMs) with symbolic systems like Knowledge Graphs. Over five stages, we will explore how to use knowledge graphs to detect hallucinations, falsehoods, contradictions, and knowledge gaps in LLM outputs. Additionally, the project will enhance LLM inference, training, and architecture to bolster model quality. Through this, we aim to establish robust mechanisms for LLM assurance and improvement.

This PhD in Computer Science project sits within the Responsible Artificial Intelligence Group at the University of Hull. The group is renowned for its work on Neuro-Symbolic AI. It consists of 7 staff members and over 10 PhD students working in areas relevant to this project. As a PhD student, you will join a growing research community in this field. This is a prestigious EPSRC (Engineering and Physical Sciences Research Council) iCASE studentship co-funded by Naimuri (A QinetiQ subsidiary).

As a PhD student, you will be expected to actively participate within the programme of study, showing good time management and organisation. You are expected to work upon and further develop the research questions posed within the research proposal, completing tasks required to gain a PhD such as attending meetings, regularly reviewing literature, completing pertinent studies, disseminating their work at appropriate forums and writing a thesis on the topic.

You will benefit from the Postgraduate Training Scheme at the University of Hull, an accredited training program designed for PhD students. It aims to enhance students' research, professional, and personal skills, preparing them for their future careers. As part of this program, you will work within the Responsible AI research group at UoH’s School of Computer Sciences. You will receive all necessary resources (including a desk, computer, and cloud-computing access) and training (academic supervision, modules, conferences, seminars, and workshops as applicable). Additionally, QinetiQ and Naimuri, a QinetiQ subsidiary, will provide industrial supervision for the project.

For informal enquiries please contact the project lead: Professor Dhaval Thakker.

Research Training

As a PhD student at the University of Hull you will undertake the Postgraduate Training Scheme alongside your main degree, to help you develop the research skills and knowledge you will need in your future career. You will gain an additional Certificate or Diploma in Research Training in additional to your PhD.

How to apply

You will need to supply a personal statement when applying for this scholarship position. Find out more about writing a personal statement. Please also ensure you include the following information:

  1. What motivates you to pursue PhD study
  2. Why you are interested in this project
  3. How your skillset matches the requirements for your choice of project and/or any additional training you will need
  4. The wider significance of research in this area and potential future research directions for the project.

Apply for the scholarship

Closing date for applications

21 May 2024

Start date

16 September 2024 

Postgraduate student reading in the Brynmor Jones Library

Watch: find out more about postgraduate study at the University of Hull


This is a prestigious EPSRC iCASE studentship co-funded by Naimuri (A QinetiQ subsidiary). The studentship covers UK PhD tuition fees and a tax-free stipend of the current UKRI rate (£18,622 in 2023/24) for 4 years.

To be accepted onto this opportunity requires the student/researcher to pass a Baseline Personnel Security Standard (BPSS) check.

This scholarship is available only for full-time study. 

Submission of Thesis

Submission of your final thesis is expected within 48 months from the start of your PhD scholarship.

Entry requirements

Applicants should hold a minimum of a 2:1 degree in a Computer Science-related subject. Prior experience in ML/AI, either through education or work, is desirable. Possessing a taught MSc or master’s by Research in a relevant field would be advantageous.

For more details on our entry requirements please visit the postgraduate admissions webpage.

This scholarship is available for full time study by Home (UK) students.