You can reach me at: m.peeperkorn@kent.ac.uk
Other online presence:

About Me

I am a PhD candidate in Computer Science at the University of Kent, advised by Anna Jordanous and Dan Brown (University of Waterloo, Canada). My PhD project focuses on the creative application of Large Language Models investigating the effects of hyperparameter choices, fine-tuning, and decoding strategies on their creative abilities. My paper “Is Temperature the Creativity Parameter of Large Language Models?” currently features on IBM Think, and was awarded the Artificial Intelligence Journal Best Student Paper Award at ICCC'24.

Currently, I am also venturing into a different research area: Neural Network Verification. As a part of Elena Botoeva's BRIGHT project I am working on learning branching heuristics. Ultimately, my aim is to research the intersection between Natural Language Processing, Creativity and Neural Network Verification to exploring formal techniques to meaningfully constrain and guide LLMs for complex natural language task, such as narrative generation.

Previously, I've worked in the creative industries as a software engineer and graphic designer, both self-employed and as part of the graphic design studio Marsdiep, specialising in unique (web-based) projects and art installations. I hold a MSc (cum laude) from the Media Technology programme at Leiden University, Netherlands and a bachelor degree in Graphic Design from the Royal Academy of Art, The Hague, Netherlands.


My research is supported by a Google PhD Fellowship in Natural Language Processing.

Publications

See my Google Scholar profile for a more complete list.

  1. Peeperkorn, M., Kouwenhoven, T., Brown, D., and Jordanous, A. (2025). Mind the Gap: Conformative Decoding to Improve Output Diversity of Instruction-Tuned Large Language Models. Preprint
  2. Peeperkorn, M., Kouwenhoven, T., Brown, D., and Jordanous, A. (2024). Is temperature the creativity parameter of large language models? In 15th International Conference on Computational Creativity. Association for Computational Creativity. ICCC’24 Best Student Paper Award
  3. Brown, D. and Peeperkorn, M. (2023). Reviewing, creativity, and algorithmic information theory. In 14th International Conference on Computational Creativity, pages 133–142. Association for Computational Creativity
  4. Peeperkorn, M., Brown, D., and Jordanous, A. (2023). On characterizations of large language models and creativity evaluation. In 14th International Conference on Computational Creativity, pages 143–147. Association for Computational Creativity
  5. Sawicki, P., Grzes, M., Goes, F., Brown, D., Peeperkorn, M., Khatun, A., and Paraskevopoulou, S. (2023b). On the power of special-purpose GPT models to create and evaluate new poetry in old styles. In 14th International Conference on Computational Creativity, pages 10–19. Association for Computational Creativity
  6. Sawicki, P., Grzes, M., Goes, F., Brown, D., Peeperkorn, M., and Khatun, A. (2023a). Bits of grass: Does GPT already know how to write like whitman? In 14th International Conference on Computational Creativity, pages 317–321. Association for Computational Creativity
  7. Peeperkorn, M. (2022). Artificial creative societies: Adaption, intention, and evaluation. In Creativity and Cognition, C&C’22, pages 704–707, New York, NY, USA. Association for Computing Machinery
  8. Peeperkorn, M., Saunders, R., Bown, O., and Jordanous, A. (2022). Mechanising conceptual spaces using variational autoencoders. In 13th International Conference on Computational Creativity, pages 287–290. Association of Computational Creativity
  9. Sawicki, P., Grzes, M., Jordanous, A., Brown, D., and Peeperkorn, M. (2022). Training GPT-2 to represent two romantic-era authors: challenges, evaluations and pitfalls. In 13th International Conference on Computational Creativity, pages 34–43. Association of Computational Creativity
  10. Peeperkorn, M., Bown, O., and Saunders, R. (2020). The maintenance of conceptual spaces through social interactions. In BNAIC/BeneLearn 2020, pages 430–431. Benelux Association for Artificial Intelligence. Master Thesis Abstract

Community

  • Program Committee

    AAAI 2026 • NeurIPS 2026 Position Paper Track • IJCAI 2025 AI, Arts and Creativity Special Track • EvoMUSART 2025 • EvoMUSART 2024
  • Reviewer

    ICML 2025 Position Paper Track • IJCAI 2024 (AI Arts and Creativity Special Track) • ICCC 2023 • IJCAI 2023 (AI Arts and Creativity Special Track)
  • Other

    Organising Committee for University of Kent PGR Conference

Art

To be added.