In this paper, the Citizen Lab’s Mohamed Amed and Jeffrey Knockel examine Chinese censorship bias in LLMs with a censorship detector they designed as part of the research. They warn that when LLMs are trained on state-censored texts, their output is more likely to align with the state.
An Analysis of Chinese Censorship Bias in LLMs was published in the Privacy Enhancing Technologies Symposium (PETS) 2025 proceedings.