Dr Piotr Sawicki

I hold a PhD in Computer Science & Artificial Intelligence from the University of Kent, where my research,  "The Digital Muse," explored the intersection of Large Language Models (LLMs) and literary art. My academic background is multidisciplinary, having previously studied Digital Visual Effects (MSc) at the School of Engineering and Computer Science (MSc). I have been a member of the School of Computing for over six years, balancing high-level NLP research with a dedicated teaching portfolio and active service to the international research community as a reviewer for ICCC 2026.

My research focuses on the capacity of generative AI to replicate and evaluate nuanced artistic styles. 

Key areas of interest include:

• Computational Creativity: Examining the evolution of creative synthesis from GPT-2 onwards.
• Natural Language Processing (NLP): Specialized fine-tuning and prompt engineering for authorial voice replication.
• Automated Evaluation: Utilizing state-of-the-art LLMs as surrogate expert judges to identify poetic quality, as published in EMNLP 2025.
• Human-AI Collaboration: Developing methodologies for user-controlled content generation in specific stylistic voices.

I lead practical lab instruction and provide technical support for the following modules:

• COMP4100: Programming I (Python) - Focus on foundational logic and debugging.
• COMP4103: Programming II (Java) - Focus on Object-Oriented paradigms (Abstraction & Inheritance).
• COMP5008: Web Development - Focus on full-stack integration and data-driven applications.

I am an active contributor to the International Conference on Computational Creativity (ICCC) and the Conference on Empirical Methods in Natural Language Processing (EMNLP). I have also contributed to the development of the "Crowd Score" methodology for evaluating AI-generated content. My work bridges the gap between theoretical AI research and practical pedagogical delivery within the School of Computing.