Back to news

AI · Article

Nous Research Says China's AI Model Political Bias Is Only a Thin Layer, Cut From 22% to 0.9%

하이테크정보 ·

At a glance

AI research company Nous Research released 'Arete-27B,' a model it trained further from Alibaba's open model Qwen3.8-27B. The share of answers that favor the Chinese government's position fell from 22% to 0.9%. The research team said this bias is shallow and sits in a relatively thin layer rather than deep in the model.

Key points

Why it matters

The same method could be used to change the answer tendencies of other AI models, so organizations using open models need to check not only performance but also how they were trained and where their data came from.

Original source

누스 리서치 "중국 AI 모델 선전 편향은 얇은 층"…미세조정으로 22%에서 0.9%로

하이테크정보 · Nov 9, 13:15 KST

Read on 하이테크정보 ↗

AI summarized the original article. Check the original for accuracy. Copyright belongs to 하이테크정보.

Other coverage

Nous Research · Ranking and more news