An Analysis of Chinese Censorship Bias in LLM
ID: 2eaff857-e99b-5999-b64e-72c9b4974ff2
STIX ID: report--2eaff857-e99b-5999-b64e-72c9b4974ff2
Feed Name: The Citizen Lab
A brief notice of a Citizen Lab paper by Mohamed Ahmed and Jeffrey Knockel on Chinese censorship bias in LLMs, describing their censorship detector and warning that models trained on state-censored texts tend to align with state narratives; the work appears in the PETS 2025 proceedings.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.