Value-based personas sampled from real survey distributions, plus a calibration step, reduce LLM prediction error on cross-country surveys especially for underrepresented populations.
On the algorithmic bias of aligning large language models with rlhf: Preference collapse and matching regularization
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
-
Improving Cross-Cultural Survey Simulation with Calibrated Value Personas
Value-based personas sampled from real survey distributions, plus a calibration step, reduce LLM prediction error on cross-country surveys especially for underrepresented populations.