Piotr Sawicki

According to our database, Piotr Sawicki authored at least 7 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Can Large Language Models Outperform Non-Experts in Poetry Evaluation? A Comparative Study Using the Consensual Assessment Technique.

Piotr Sawicki, Marek Grzes, Dan Brown, Fabrício Góes

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2023

On the power of special-purpose GPT models to create and evaluate new poetry in old styles.

Piotr Sawicki, Marek Grzes, Fabrício Góes, Anna Jordanous, Dan Brown, Simona Paraskevopoulou, Max Peeperkorn, Aisha Khatun

Proceedings of the 14th International Conference on Computational Creativity, 2023

Bits of Grass: Does GPT already know how to write like Whitman?

Piotr Sawicki, Marek Grzes, Fabrício Góes, Dan Brown, Max Peeperkorn, Aisha Khatun

Proceedings of the 14th International Conference on Computational Creativity, 2023

Pushing GPT's Creativity to Its Limits: Alternative Uses and Torrance Tests.

Fabrício Góes, Piotr Sawicki, Marek Grzes, Marco Volpe, Jacob Watson

Proceedings of the 14th International Conference on Computational Creativity, 2023

Is GPT-4 Good Enough to Evaluate Jokes?

Fabrício Góes, Piotr Sawicki, Marek Grzes, Marco Volpe, Dan Brown

Proceedings of the 14th International Conference on Computational Creativity, 2023

2022

Crowd Score: A Method for the Evaluation of Jokes using Large Language Model AI Voters as Judges.

Fabrício Góes, Zisen Zhou, Piotr Sawicki, Marek Grzes, Daniel G. Brown

CoRR, 2022

Training GPT-2 to represent two Romantic-era authors: challenges, evaluations and pitfalls.

Piotr Sawicki, Marek Grzes, Anna Jordanous, Dan Brown, Max Peeperkorn

Proceedings of the 13th International Conference on Computational Creativity, 2022