Roger Beaty

Assessing and Enhancing Human Creativity with AI

The subjective human assessment of creativity has long stood as the gold standard. Now, advances in AI allow computational systems to mimic human creativity evaluation. I will present recent work on computational creativity assessment, from large language models assessing design solutions to convolutional neural networks judging sketches. A key benefit of AI assessment is the ability to provide real-time feedback during the creative process. AI feedback can boost creative performance and facilitate metacognitive reflection, helping people become more accurate in evaluating their ideas. I will discuss challenges in automating creativity assessment, including avoiding algorithmic bias and aligning with human values.

Roger Beaty is the Dr. Frances Keesler Graham Early Career Professor and Director of the

Cognitive Neuroscience of Creativity Lab at Penn State University. His lab studies the psychology and neuroscience of creativity using psychometric, computational, and brain imaging methods. He received the Berlyne Award for early career contributions to creativity research from the American Psychological Association. His research on computational creativity assessment is funded by the National Science Foundation and the Army Research Institute. He is an Associate Editor for Creativity Research Journal, and he serves on the Executive Committee of the Society for the Neuroscience of Creativity.