Document Type
Poster
Publication Date
Fall 2025
Abstract
This project explores the feasibility of using a Large Language Model (LLM) to provide technical ballet critiques, a task traditionally reliant on oral tradition and person-toperson instruction. To test accuracy, current-day ballet technical standards were applied to clips of Leslie Caron in the 1951 film An American in Paris. Seven clips of classical ballet were analyzed by both the researcher (a dancer with 15 years of pre-professional training) and Gemini. Using a structured, technique-focused prompt, the LLM was tasked with providing technical corrections. The results were compared to evaluate whether an AI can accurately identify specific technical flaws in real-time movement.
Recommended Citation
Enright, Anne-Duncan, "AI Ballet Corrections: Applying Current Ballet Technique to An American in Paris" (2025). IPHS 391: Interdisciplinary AI Frontiers. Paper 9.
https://digital.kenyon.edu/dh_iphs_391/9
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.