Verbalized Rejection Sampling reduces bias in LLM Bernoulli sampling by prompting the model to reason about and accept or reject proposed samples.
Political Analysis , 31(3):337–351
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
GEMS formulates close-ended human-behavior simulation as link prediction on a heterogeneous graph and matches or exceeds LLM performance with three orders of magnitude fewer parameters across three datasets and three evaluation settings.
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.
LLM annotators exhibit model-specific social-desirability biases on CSS tasks that standard prompts fail to correct and that can produce misleading aggregate statistics via accidental cancellation.
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.
-
Graph-Based Alternatives to LLMs for Human Simulation
GEMS formulates close-ended human-behavior simulation as link prediction on a heterogeneous graph and matches or exceeds LLM performance with three orders of magnitude fewer parameters across three datasets and three evaluation settings.
-
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.
-
Two Wrongs, No Right: Auditing Social-Desirability Bias in LLM Annotators for Computational Social Science
LLM annotators exhibit model-specific social-desirability biases on CSS tasks that standard prompts fail to correct and that can produce misleading aggregate statistics via accidental cancellation.