The signal is the ceiling: Measurement limits of LLM-predicted experience ratings from open-ended survey text
arXiv:2604.19645v1 Announce Type: new
Abstract: An earlier paper (Hong, Potteiger, and Zapata 2026) established that an unoptimized GPT 4.1 prompt predicts fan-reported experience ratings within one point 67% of the time from open-ended survey text. T…