# Nous Research — Introducing Arete-27B: Qwen3.8-27B Post-Trained To Reinforce Western Values

- Company: Nous Research (nousresearch.com)
- Announced: 2026-11-06T15:00:00+00:00
- Category: new-model
- Coverage: 4 outlets
- Announcement: yes
- Group: models
- Source: https://nousresearch.com/arete
- Record: https://forck.live/items/32872-introducing-arete-27b-qwen3-8-27b-post-trained-to-reinforce-western-values
- Subject: Hermes models
- Open weights: yes
- Models affected: Arete-27B, Qwen3.8-27B

Nous Research post-trained Alibaba's Qwen3.8-27B to reinforce Western values and released the result as Arete-27B, an open-weight model built on a Chinese-trained base. Nous says it observed refusals, deflections and CCP-framed answers on politically sensitive topics in Qwen3.8-27B and trained to alter those biases, though it does not claim to have remedied every behaviour tied to that viewpoint. To measure the change, Nous built an evaluation of 803 prompts across seven value categories, including freedom of expression, state ideology, democracy and data privacy, scoring answers on factual recall and on whether they adopt the Chinese state's account. Each prompt carries 2–4 required facts drawn from a dated source article, and an LLM judge, Grok 4.7, marks each fact stated, missed or opposed without being told which model wrote the answer. Nous says it chose Qwen3.8-27B because it was the most performant local model and showed much of the behaviour it targeted, and it removed training prompts overlapping the evaluation set. The evaluation is open, with all 803 prompts, their source articles and required facts, the judge prompt, and scripts to grade and score other models.

## Around this story

Outlets this record can name and link:

- The Decoder — State propaganda in some Chinese AI models is only "a thin layer" that fine-tuning can strip away: https://the-decoder.com/state-propaganda-in-some-chinese-ai-models-is-only-a-thin-layer-that-fine-tuning-can-strip-away
- Implicator — Nous Research's Arete-27B Strips Propaganda From Alibaba's Q: https://implicator.ai/nous-research-unveils-arete-27b-post-trained-qwen3-8-27b
- Gigazine — 中国製AI「Qwen3.8-27B」の中国政府寄りの回答を減らしたAI「Arete-27B」が登場、プロパガンダを含む回答が22％から0.9％に減少: https://gigazine.net/news/20261109-nous-research-arete-27b
- Neoteo — Qwen 3.8 pro-Beijing answers in Nous's Arete-27B test: https://neoteo.com/en/nous-says-arete-27b-cut-qwens-pro-beijing-framing-rate

---

Record: https://forck.live/items/32872-introducing-arete-27b-qwen3-8-27b-post-trained-to-reinforce-western-values
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md
