While detecting and avoiding bias in LLM-generated text is becoming increasingly important, media bias often remains subtle and subjective, making it particularly difficult to identify and mitigate. In this study, we assess media bias in LLM-generated content and LLMs' ability to detect subtle ideological bias. We conduct this evaluation using two datasets, PoliGen and EconoLex, covering political and economic discourse, respectively. We evaluate eight widely used LLMs by prompting them to generate articles and analyze their ideological preferences via self-assessment. By using self-assessment, the study aims to directly measure the models' biases rather than relying on external interpretations, thereby minimizing subjective judgments about media bias. Our results reveal a consistent preference of Democratic over Republican positions across all models. Conversely, in economic topics, biases vary among Western LLMs, while those developed in China lean more strongly toward socialism.
View on arXiv@article{kennedy2025_2503.16674,
title={ Through the LLM Looking Glass: A Socratic Self-Assessment of Donkeys, Elephants, and Markets },
author={ Molly Kennedy and Ayyoob Imani and Timo Spinde and Hinrich Schütze },
journal={arXiv preprint arXiv:2503.16674},
year={ 2025 }
}