Just a recommended reading at this stage, the authors attempt to get discrimination and difficulty from artificial crowds, or LLMs that repeatedly answer the items, and then analyze the data conventionally:
Laverghetta Jr, A., Nighojkar, A., Mirzakhalov, J., & Licato, J. (2021, July). Predicting human psychometric properties using computational language models. In The Annual Meeting of the Psychometric Society (pp. 151-169). Cham: Springer International Publishing.
Next page
Last page
Exploring embedding compositions
Return home
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).
