S. Atreja, J. Ashkinaze, L. Li, J. Mendelsohn, and L. Hemphill, “What’s in a Prompt?: A Large-Scale Experiment to Assess the Impact of Prompt Design on the Compliance and Accuracy of LLM-Generated Text Annotations”, ICWSM, vol. 19, no. 1, pp. 122–145, Jun. 2025.