annotation validation 1conversation analysis 1customer satisfaction 1large language models 1multidimensional rating 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.CL2026
Dimensionality in Satisfaction Ratings
Andrew Hong, Jason Potteiger
The paper uses GPT‑4.1 to annotate about 9,000 customer‑service conversations, breaking satisfaction into overall, agent, outcome, product, and effort dimensions, and compares thes…
cs.CL2026
The signal is the ceiling: Measurement limits of LLM-predicted experience ratings from open-ended survey text
Andrew Hong, Jason Potteiger, Luis E. Zapata
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 op…
cs.CL2026
LLM Predictive Scoring and Validation: Inferring Experience Ratings from Unstructured Text
Jason Potteiger, Andrew Hong, Ito Zapata
We tasked GPT-4.1 to read what baseball fans wrote about their game-day experience and predict the overall experience rating each fan gave on a 0-10 survey scale. The model receive…