2 papers
stat.AP2026
Can Large Language Model-Generated Responses Support Assessment Development? A Human-Calibrated Rasch Benchmark
Eunjeong Song, Sehee Hong
Large language models (LLMs) are proposed as synthetic respondents for pilot testing, but their usefulness depends on whether they supply the evidence assessment development requir…
cs.CY2026
Diagnosing the Demographic Distributions of LLM-Based Synthetic Persona Data: Reference-Distribution Dependence and Post Hoc Adjustment
Eunjeong Song, Sehee Hong
We examine how strongly demographic-distribution diagnostics of LLM-based synthetic persona data depend on the official statistics chosen as the reference. We compared the sex $\ti…