LLM digital personas improve alignment with human survey response distributions for stable attributes but remain limited for individual prediction and fail to recover multivariate respondent structure.
On failure, the invalid response and the associated error message are appended to the prompt, and the call is reissued
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
When Can Digital Personas Reliably Approximate Human Survey Findings?
LLM digital personas improve alignment with human survey response distributions for stable attributes but remain limited for individual prediction and fail to recover multivariate respondent structure.