Skip to content

Nous Research fine-tunes Qwen3.8-27B to release Arete-27B

What happened

AI digest

On 7 November 2026, The Decoder reported that Nous Research supervised-fine-tuned Alibaba's Qwen3.8-27B on about 53 million tokens to produce the open-weight model Arete-27B. According to the report, the model's share of promotional answers fell from 22% to 0.9%, while factual accuracy rose from 2.32 to 2.98. This is the only report on the matter so far, with no follow-up developments or contradictions with earlier coverage.

Written by AI from the reports · updated 8 d ago

Timeline

Follow the reports to see the event from each side.

Nov 7
  1. The Decoder
    State propaganda in some Chinese AI models is only "a thin layer" that fine-tuning can strip away

    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. The political bias is "applied late, it is applied thin," the team writes.

Heat of this event

Current heat 3·Peak in the comparable range 4(Nov 9 09:00)·Change over 24 hours in the comparable range –

01234Nov 909:00Nov 913:00Nov 916:00Nov 920:00

The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.