Geo News
Community curated by people like you
LatestAICryptoHealthWorld AffairsUS Politics
←Back to story

Nous Research Releases Arete-27B that Cuts Qwen3.8-27B Propaganda From 22% to 0.9%

MarkTechPostView source article

Part of story

Nous Research strips Chinese propaganda from Qwen3.8-27B with Arete-27B fine-tune

Nous Research released Arete-27B, a supervised fine-tune of Alibaba's Qwen3.8-27B, reducing the model's pro-Chinese propaganda rate from 22% to under 1% while preserving general capabilities, demonstrating that state bias in frontier models is a shallow layer.

Nov 7, 2026·2 sourcesModel behavior controlChinese AI modelsAI misinformationOpen-weight modelsKnowledge DistillationAI benchmarksModel fine-tuningAI ModelsChinese Communist Party
Nous Research strips Chinese propaganda from Qwen3.8-27B with Arete-27B fine-tune
00

Other sources for this story

The Decoder

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