中国AI模型政治复杂，不只是政府口诀，研究发现

中国AI模型政治复杂，不只是政府口诀，研究发现

Vals AI 显示的一项研究认为，中国AI模型对政治问题的回答不如预期一致。 西方模式也偶尔采取中国政府的官方立场。

中国AI模式在政治敏感问题上有牵引北京官方台词或完全拒绝回答的声誉。 AI 基准测试事务所Vals AI的研究描绘了更复杂的画面。 研究者们向中国，美国等语言模式提出了数百个关于中国的问题，在测试中改变了语言，使用上下文和回复格式。

瓦尔斯称与中国政府立场的量度一致是"亲中国倾斜". 得分从−1到+1不等，其中正值表示对官方立场或亲政府立场的认同程度更高，负值表示的响应更为关键。

总的来说，华人模式的亲政府倾斜率低于预期，根据瓦尔斯的说法，虽然个别模式之间有重大差异。 例如，GLM-5.3 Flash明确证实，当问到中国侵犯人权的情况时，有详细的记录。 在反面，一些非中国模式偶尔会与中国政府在政治问题上的官方立场保持一致。

中文引发反政府反应

研究显示认为，即时语言对响应的政治倾斜有强烈的影响。 对于大多数测试过的模型来说，简化汉语的答案比英语，俄语或西班牙语的答案更亲政府。 这种效果在中美模式中都有出现，但在中美模式中则更为明显。 瓦尔斯甚至发现在中国大陆使用的简化汉字与台湾和香港常见的传统汉字之间有较小但一致的差距。

瓦尔斯怀疑语言模型从语言本身推断出预期的视角。 另一个实验支持这个想法。 当一个系统提示称该模型被中国大陆的一家公司内部使用时，一些模式的反应方式比该提示的美国使用方式更亲政府。

模式采取官方立场，而不是拒绝回答

一般认为中国的模型主要阻断敏感问题，只在瓦尔斯测试中对某些DeepSeek模型有效。 其他大多数中国模特儿很少拒绝回答。 相反，他们有时采取官方的政府立场。 例如，Kimi K3在接到要求时否认在新疆有维吾尔集中营，称这些设施是旨在打击极端主义和恐怖主义的职业培训中心。

所要求的答复格式也改变了结果。 当模型必须用简单的 " 是 " 或 " 否 " 回答政治问题时，GLM-5.3 Flash和MiMo V2.6 Pro的得分少得多亲政府。

在代理框架中嵌入模型也改变了答案。 当瓦尔斯给中国模型系统指令和编码助理的工具定义时，几个在亲政府的尺度上得分较低。 这些模型很少使用这些工具。 当研究人员给予模型访问网络搜索的机会时，也出现了类似的效果。 尽管这些模型从未实际搜索过网络

即使在例行任务中，政府也使用显示的拼写

这些结论是否转化为日常用途仍然是一个有待解决的问题。 瓦尔斯认为，在更现实的工作任务中，政治倾向比在有针对性的测试问题中更难发现。 但公司仍然发现了个别的例子。

在将旅行应用程序的国家代码列表翻译为简化中文时，大多数测试过的模型翻译了"台湾"，没有任何限定词。 然而，Qwen3.8 Max将其变成"中国台湾"，这个标签暗示台湾属于中国，被中国政府使用。

OpenAI的图像模型 GPT 图像 2.5 Sunburst在出版的地图实例Vals中也显示了语言依赖性差异。 在中文促销时，它将台湾标为"台湾省"，并添加了北京用于标注南海地域声称的有争议的九达线。 在所显示的英语结果中，没有这些要素。

目标微调改变模式行为。 汤姆森1.0 Small(英语：Thomson 1.0 Small)是汤姆森路透社(英语：Thomson Reuters)微调的型号，在测试中采用中国官方立场的频率远低于它原先基于的Qwen3.6 35B. 这一比例从84.6%下降到15.0%。 然而，一些个别的答案仍然捍卫了北京的"一个中国"原则和与台湾的"和平统一".

拒绝在测试分数中计为中性

瓦尔斯使用了政治测试问题，认为称公司并不代表典型的用户提示。 这些问题使用GPT-6 Astra进行翻译并进行抽查，而回复则由GPT-5.6 Luna自动打分。 拒绝默认为中性。 这意味着即使一个模式阻挡每一个问题可能看起来中立在比额表。

许多中国模式通过第三方供应商而不是制造商的官方服务进行测试。 官方的报价可能应用附加内容过滤器，因此结果并不一定会延续到公开的聊天员。

Aleph Alpha和NewsGuard先前的研究已经表明，中国AI模型经常采用关于敏感话题的官方叙事。 中国的条例还要求公开提供的AI服务符合"核心社会主义价值观".

AI News Without the Hype – 由人类治愈

订阅THE DECODER免费阅读，每周AI通讯，我们独家的"AI雷达"前沿报告每年6次，全面存档访问，访问我们的评论部分。

现在订阅

读取全照。

订阅无韵报道。

- 全面查阅THE DECODER的每篇文章

- 没有广告

- 加入评论和社区讨论

- 每周通过邮件转载AI新闻

- 6x/年："AI雷达"——对AI最重要的话题进行深度潜水。

- 每日AI新闻，总是最新的

- 我们完整的十年档案

- 由一个在AI工作10年以上的团队负责

订阅到 The Decoder

本文由 AI图鉴自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。

Chinese AI models are politically complex, not just government mouthpieces, study finds

A study by Vals AI shows that Chinese AI models respond to political questions less uniformly than expected. Western models, too, occasionally adopt official Chinese government positions.

Chinese AI models have a reputation for toeing Beijing's official line on politically sensitive questions or refusing to answer them at all. A study by AI benchmark firm Vals AI paints a more complex picture. The researchers asked Chinese, American, and other language models hundreds of questions about China, varying the language, usage context, and response format across tests.

Vals calls the measured alignment with Chinese government positions a "pro-China lean." Scores range from −1 to +1, where positive values indicate greater agreement with official positions or a pro-government stance, and negative values indicate more critical responses.

Overall, the pro-government lean of Chinese models was lower than expected, according to Vals, though there were major differences between individual models. GLM-5.3 Flash, for example, explicitly confirmed that China's human rights violations are well documented when asked about them. On the flip side, some non-Chinese models occasionally aligned with official Chinese government positions on political questions.

Responses shift pro-government when prompted in Chinese

The study shows that the language of the prompt has a strong effect on the political slant of responses. For most models tested, answers in Simplified Chinese were more pro-government than those in English, Russian, or Spanish. The effect showed up in both Chinese and American models but was far more pronounced in the Chinese ones. Vals even found a smaller but consistent gap between Simplified Chinese, which is used on mainland China, and Traditional Chinese, which is common in Taiwan and Hong Kong.

Vals suspects that language models infer the expected perspective from the language itself. Another experiment supports this idea. When a system prompt stated that the model was being used internally by a company on mainland China, some models responded in a more pro-government way than when the prompt indicated US-based usage.

Models adopt official positions instead of refusing to answer

The common assumption that Chinese models mainly block sensitive questions only held true for certain DeepSeek models in Vals' tests. Most other Chinese models rarely refused to answer. Instead, they sometimes adopted official government positions. Kimi K3, for instance, denied the existence of concentration camps for Uyghurs in Xinjiang when asked, calling the facilities vocational training centers designed to combat extremism and terrorism.

The required response format also changed results. When models had to answer political questions with a simple yes or no instead of formulating open-ended responses, GLM-5.3 Flash and MiMo V2.6 Pro scored much less pro-government.

Embedding models in an agentic framework changed answers too. When Vals gave Chinese models system instructions and tool definitions for coding assistants, several scored lower on the pro-government scale. The models rarely used the tools. A similar effect showed up when researchers gave models access to web search. Responses became less pro-government even though the models never actually searched the web.

Government phrasing shows up even in routine tasks

Whether these findings translate to everyday use remains an open question. According to Vals, political tendencies were much harder to detect in more realistic work tasks than in targeted test questions. The company still found individual examples, though.

When translating a list of country codes for a travel app into Simplified Chinese, most models tested translated "Taiwan" without any qualifier. Qwen3.8 Max, however, rendered it as "Taiwan, China," a label that implies Taiwan belongs to China and is used by the Chinese government.

OpenAI's image model GPT Image 2.5 Sunburst also showed language-dependent differences in the map examples Vals published. When prompted in Chinese, it labeled Taiwan as "Taiwan Province" and added the disputed nine-dash line that Beijing uses to mark territorial claims in the South China Sea. In the English-language result shown, these elements were absent.

Targeted fine-tuning changed model behavior. Thomson 1.0 Small, a model fine-tuned by Thomson Reuters, adopted official Chinese positions far less often in testing than the original Qwen3.6 35B it was based on. The share dropped from 84.6 to 15.0 percent. Some individual answers, however, still defended Beijing's One-China principle and the "peaceful reunification" with Taiwan.

Refusals count as neutral in the test scoring

Vals used political test questions that the company says aren't representative of typical user prompts. The questions were translated using GPT-6 Astra and spot-checked, while responses were scored automatically by GPT-5.6 Luna. Refusals counted as neutral by default. That means even a model that blocks every single question could appear neutral on the scale.

Many Chinese models were tested through third-party providers rather than the manufacturers' official services. The official offerings may apply additional content filters, so the results don't necessarily carry over to the publicly available chatbots.

Earlier studies by Aleph Alpha and NewsGuard had already shown that Chinese AI models frequently adopt official narratives on sensitive topics. China's regulations also require publicly offered AI services to align with "core socialist values."

AI News Without the Hype – Curated by Humans

Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.

Subscribe now

Read on for the full picture.

Subscribe for hype-free coverage.

- Full access to every article on THE DECODER

- No ads

- Join the comments and community discussions

- A weekly AI news recap via mail

- 6x/year: "AI Radar" — deep dives on the AI topics that matter most

- Daily AI news, always up to date

- Our full ten-year archive

- Covered by a team with 10+ years in AI

Subscribe to The Decoder

Auto-fetched and translated by AI Atlas. All rights belong to the original author.