Six language models left human respondents uncovered in synthetic survey generation
Researchers evaluated six language models on their ability to generate synthetic survey respondents and found that all of them left human respondents uncovered when measured by respondent coverage gap.
Every language model tested had a higher respondent coverage gap than a Gaussian copula fitted to the human data across the prompting and inference settings evaluated.
Sources behind this report
Report history
No earlier revision dates are retained here. This does not establish that the report has never changed; read any dated updates and corrections.
This brief was made by AI and checked against its cited public sources. How the newsroom works