Interview-informed LLMs roughly reproduced average BREQ item responses but underestimated human variability and failed to recover the test's psychometric structure.
ashamed”, “failure
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Leveraging Interview-Informed LLMs to Model Survey Responses: Comparative Insights from AI-Generated and Human Data
Interview-informed LLMs roughly reproduced average BREQ item responses but underestimated human variability and failed to recover the test's psychometric structure.