Models
Nous Research releases Arete-27B, a Qwen3.8-27B fine-tuned on Western values, and says Chinese state bias is a thin layer, a conclusion based on its own 803-prompt test
Nous Research fine-tuned Qwen3.8-27B into Arete-27B and says state bias is superficial; its own 803-prompt test shows propaganda falling from 22% to 0.9%.
Nous Research announced Arete-27B on November 6, 2026, a version of Alibaba's Qwen3.8-27B post-trained on about 53 million tokens to reinforce what the lab calls Western values. It reports that answers containing propaganda fell from 22% to 0.9% on its own 803-prompt evaluation. The framing needs a limit: this is a fine-tune, not a retraining from scratch, the test and the definition of Western values are Nous's own, and the thin-layer conclusion is the lab's interpretation, not an independent finding.
The essentials
- What was released: Arete-27B, a post-trained Qwen3.8-27B, with weights, the evaluation and training data published under Apache 2.0 on Hugging Face, per The Decoder.
- The headline number: on Nous's 803-prompt test across seven value categories, the share of answers with propaganda fell from 22% to 0.9% (rounded to 1% in the announcement), and a fact score rose from 2.32 to 2.98 out of 5.
- Capabilities: on Hermes Bench, Nous's internal benchmark, Arete scores 65.60% against 65.77% for the base model, which Nous calls noise.
- The claim: Nous says the bias is superficial and that the values in an open model are one fine-tune away. That reading is the lab's own.
What the test can and cannot show
The 803 prompts, the seven categories and the rubric for what counts as propaganda were all written by Nous, and the main runs use temperature 0 for Arete and the base model but 0.6 for the other models compared. A drop on this test shows the model now answers differently on these prompts; it does not by itself show that the underlying knowledge or behaviour elsewhere is unchanged. AlphaSignal notes that the evaluation measures conformance to a defined value policy rather than a viewpoint-free alignment.
Why it matters beyond Qwen
The Decoder frames the result as evidence that political bias in Chinese open-weight models can be stripped cheaply. The same method can in principle push a model in any direction, which is also the point Nous makes. Nous Research raised 90 million dollars in a Series B in October at a 1.5 billion dollar valuation, per The Decoder.
What is not established
- Independent replication of the 22% to 0.9% result: not seen.
- Whether the thin-layer conclusion holds on other prompts or other models: not established.
- How Arete behaves on topics outside the 803 prompts: not tested in the sources we read.
- Whether the Western-values rubric is neutral: it is defined by Nous, not an external standard.
Summary table
| Point | What is stated as of November 7, 2026 | Source |
|---|---|---|
| Release | Announced November 6, 2026; weights, eval and data public | Digg |
| Base model | Alibaba's Qwen3.8-27B, post-trained on about 53 million tokens | The Decoder |
| Propaganda rate | 22% to 0.9% on Nous's 803-prompt test | Nous Research |
| General capability | Hermes Bench 65.60% vs 65.77%, an internal test | Nous Research |
| License | Apache 2.0 on Hugging Face | The Decoder |
FAQ
Is Arete-27B a new model?
It is a fine-tune of Alibaba's Qwen3.8-27B, not a model trained from scratch.
Does it prove Chinese AI bias is superficial?
Not independently. It is Nous's own reading of its own test; replication by others has not been seen.
Can I use it?
Nous published the weights, evaluation and training data under Apache 2.0 on Hugging Face, per The Decoder.
Method and limits
Sources checked on November 8, 2026. We read search excerpts of the Nous Research page and X post, not the full blog post or the model card, and relied on The Decoder, Digg, AlphaSignal and Pasquale Pillitteri for details. All figures are Nous's. This is not an endorsement of any political value set.
Sources
- Nous Research: Introducing Arete-27B: Qwen3.8-27B Post-Trained To Reinforce Western Values (verified 2026-11-08)
- The Decoder: State propaganda in some Chinese AI models is only “a thin layer” that fine-tuning can strip away (verified 2026-11-08)
- Digg: Nous gives Qwen a “Western values” makeover with Arete-27B (verified 2026-11-08)
- AlphaSignal: Nous Research's Arete-27B Cuts Chinese State-Aligned Responses by 95% (verified 2026-11-08)
- Pasquale Pillitteri: Nous Research launches Arete-27B and cuts Qwen's propaganda rate from 22% to 1% (verified 2026-11-08)
Spotted an error in this article? Report it · Our corrections policy