NCME talk: generative psychometrics validates LLM-generated test items before human data

GolinoHudson · x · 2026-11-19

Hudson Golino (University of Virginia) will present on Nov 18 (4 pm ET) at NCME's SIGIMIE talk series a "generative psychometrics" framework that pairs LLM-based automatic item generation with computational structural-validity checks.

The workflow uses construct definitions to guide item generation, then feeds LLM embeddings into Exploratory Graph Analysis (EGA), unique variable analysis, and bootEGA to flag redundant and unstable items — providing an in-silico screening stage before collecting human response data. The talk also covers how model dependence, prompting technique, and construct definition affect results.

Original post →

More from Research

Research channel →