Recent advances in artificial intelligence (AI), particularly large language models (LLMs) and multimodal systems, present transformative opportunities for educational assessment. This PhD research proposes the development of an explainable, multimodal AI framework for automatically evaluating high-stakes student examinations, such as UK A-levels, which often contain complex textual responses, diagrams, and structured problem-solving steps. The project addresses key limitations of current automated assessment systems—including lack of transparency, inability to process visual content, and misalignment with pedagogical goals—by integrating state-of-the-art natural language processing, computer vision, and interpretability techniques. Developed in collaboration with AQA, the UK’s leading examination board, this research will produce an AI system capable of accurate scoring, personalized feedback generation, and human-understandable explanations of its decision-making process. The study employs a mixed-methods approach, combining technical development (e.g., fine-tuned LLMs, multimodal fusion architectures) with rigorous educational validation (e.g., expert reviews, fairness audits). Key innovations include novel methods for aligning AI assessments with curriculum standards, quantifying model explainability in educational contexts, and generating actionable feedback to support student learning. By bridging AI and education research, this work aims to establish best practices for trustworthy, pedagogically sound AI assessment systems while contributing open-source tools and datasets to the research community. The outcomes will provide critical insights for policymakers and educators seeking to leverage AI’s potential in high-stakes assessment environments—ensuring both technological advancement and educational equity.

A dissertation submitted in partial fulfillment of the requirements for the degree of M.Sc. Data Science (School of Engineering & Informatics). University of Wolverhampton 2025.

Its a trial for my MSC project

This report, created using Quarto in RStudio(Bauer and Landesvatter 2023), provides a visual analysis of a snapshot extracted from data of 2021 household census in England. Using ggplot2, we explore key demographic trends, focusing on factors like age, income, marital status and ethnicity. The main objective is to process the data which can be used to obtain interesting patterns and linear relationships between the variables through clear visualizations (Hoffmann 2021). The report offers insights that could inform future policies and improve understanding of the correlation between the variables.