cs.LGNov 13, 2026

Revealing the Biases of Large Language Models By Inferring Prior Distributions

Authors: Joshua Ryo Cheng, Thomas L. Griffiths, Jake C. Snell

Organizations: Department of Mathematics, Princeton University · Department of Computer Science, Princeton University · Department of Psychology, Princeton University

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.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. CogBias: Measuring and Mitigating Cognitive Bias in Large Language Models

    Apr 1, 2026Fan Huang, Songheng Zhang, Haewoon Kwak +1Cognitive Bias in Language ModelsLanguage Model Bias Evaluation

  2. Measuring Human-Like Bias in LLMs? A Critique of Human-Derived Bias Constructs in LLM Evaluation

    Sep 4, 2026Antonela Tommasel, Markus SchedlCognitive Bias in Language ModelsLanguage Model Bias Evaluation