How Bias Amplifies Across AI Generations

This study combines WMLE with qualitative media analysis to reveal how generative AI models amplify political bias—especially through story framing and word choice—across successive outputs.

Table of Links

A. Mathematical Formulation of WMLE

B Fine-tuning Setup

C Qualitative Bias Analysis Framework and Example of Bias Amplification Across Generations

D Distribution of Text Quality Index Across Generations

E Average Perplexity Across Generations

F Example of Quality Deterioration Across Generations

G Pearson Correlation Between Neuron Weight and Bias Performance | H Pearson Correlation Between Neuron Weight and Generation Quality | I Pearson Correlation Between Neuron Activation and Bias Performance | J Pearson Correlation Between Neuron Activation and Generation Quality | K Mathematical Details for the Statistical Tests | L Literature Review of Model Collapse

A Mathematical Formulation of WMLE

In Weighted Maximum Likelihood Estimation, we maximize the weighted log-likelihood:

B Fine-tuning Setup

C Qualitative Bias Analysis ...