Fine-tuning LLMs to match country-level survey response distributions with a first-token KL-divergence loss gives modest but consistent accuracy gains over zero-shot prompting, while remaining far from reliable on unseen questions.
Title resolution pending
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
-
Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations
Fine-tuning LLMs to match country-level survey response distributions with a first-token KL-divergence loss gives modest but consistent accuracy gains over zero-shot prompting, while remaining far from reliable on unseen questions.