arXiv · 2611.18996
Revealing the Biases of Large Language Models By Inferring Prior Distributions
Abstract
Large Language Models (LLMs) have been known to exhibit a wide range of social biases including name-nationality associations, occupation-gender associations and racial stereotypes. Existing approaches to evaluating these biases typically involve measuring surface-level behavior where a model is fed a dataset of prompts and its outputs are scored relative to ground-truth answers. Inspired by prior elicitation in cognitive science, we propose a different perspective that reconstructs latent bias as a prior underlying the model's behavior. We formulate the problem as a Bayesian inverse problem where, given prompt-response observations on a bias benchmark dataset, we infer a low-dimensional latent distribution that summarizes the model's stereotyping tendencies. This paper develops the mathematical foundation, a practical reconstruction algorithm, and experiments using the Bias Benchmark for QA (BBQ) benchmark to infer the prior distributions of LLMs over responses in ambiguous social contexts.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Joshua Ryo Cheng, Thomas L. Griffiths, Jake C. Snell. 2026-11-13. Revealing the Biases of Large Language Models By Inferring Prior Distributions. https://searcharxiv.com/abs/2611.18996
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.