Synapse Open Synapse
AI

State propaganda in some Chinese AI models is only "a thin layer" that fine-tuning can strip away

The Decoder · · 4 min read

Nous Research retrained Alibaba's Qwen3.8-27B to produce Arete-27B, largely stripping out its pro-Chinese bias. The propaganda rate dropped from 22 percent to less than one percent, while general capabilities remained intact in tests. The method relied on 53 million tokens of supervised fine-tuning.

Latest from The Decoder