Nous Research 基于 Qwen3.8-27B 后训练出 Arete-27B，降低中文价值观倾向
Nous Research 把 Qwen3.8-27B 微调成价值观倾向接近西方模型的 Arete-27B，官方立场率从 22% 降到 1%，权重和数据全开源，做对齐研究的可以看看。
Nous Research 发布 Arete-27B，基于 Qwen3.8-27B 做后训练，目标是弱化权重中的中国官方立场行为。团队构建了覆盖言论自由、民主、隐私等七个价值类别的 803 条提示词评估集，微调用约 5300 万 token，将模型的中国官方立场采纳率从 22% 降到 1%，与测试的西方模型持平。Hermes Bench 成绩显示性能没有明显损失，权重、评估集和训练数据均已开源。
呃.. 所以是用 Qwen3.8-27B 后训练了一个“德性”模型？还是强化西方价值观的德性？ 是不是类似于收养一个中国孩子，然后不断给他灌输洗脑西方知识，让他误以为自己是美国孩子？ 所以，Nous Research 你就不能收养个美国孩子？啥？美国没有 Qwen 这么听话的孩子？ 那你就自己生一个纯血美国孩子呗。 Nous Research @NousResearch Introducing Arete-27B: Qwen3.8-27B, post-trained to reinforce Western values. Chinese open models are currently the strongest available, but they ship with state-aligned behavior in the weights. We built an 803-prompt eval across seven value categories, including freedom of expression, democracy, and privacy, and measured how often a model adopts China’s party line. After fine-tuning on roughly 53 million tokens, Arete-27B's propaganda rate fell from 22% to 1%, in line with the Western models we tested. Its Hermes Bench score shows no significant performance tradeoffs. The values in an open model are one fine-tune away. Our eval, weights, and training data are available now along with the full blog post: nousresearch.com/arete Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 1 👀 205 ⚡
