# 一些中国人工智能模型中的国家宣传只是微调可以剥离的“薄层”

> 全文为英语

**Published:** 2026年11月7日
**Author:** Jonathan Kemper
**Source:** The Decoder
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/state-propaganda-in-some-chinese-ai-models-is-only-a-thin-layer-that-fin

Nous Research 对阿里巴巴的 Qwen3.8-27B 进行了重新训练，以生产 Arete-27B，很大程度上消除了其亲中国的偏见。宣传率从22%下降到不足1%，而总体能力在测试中保持完好。该方法依赖于……的 5300 万个代币。

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. The article State propaganda in some Chinese AI models is only "a thin layer" that fine-tuning can strip away appeared first on The Decoder.

---

*内容来自原始来源： [The Decoder](https://the-decoder.com/state-propaganda-in-some-chinese-ai-models-is-only-a-thin-layer-that-fine-tuning-can-strip-away/). 查看原文.*

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*