Verbalized Rejection Sampling reduces bias in LLM Bernoulli sampling by prompting the model to reason about and accept or reject proposed samples.
Technical report, National Bureau of Economic Research
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2verdicts
UNVERDICTED 2representative citing papers
Fine-tuning LLMs on the SubPOP dataset of 3,362 questions and 70K pairs reduces the gap between LLM predictions and human survey responses by up to 46% and generalizes to unseen surveys and subpopulations.
citing papers explorer
-
Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling
Verbalized Rejection Sampling reduces bias in LLM Bernoulli sampling by prompting the model to reason about and accept or reject proposed samples.
-
Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions
Fine-tuning LLMs on the SubPOP dataset of 3,362 questions and 70K pairs reduces the gap between LLM predictions and human survey responses by up to 46% and generalizes to unseen surveys and subpopulations.