研究称中国AI模型在敏感话题上重复官方立场或拒答
原标题：Chinese AI models parrot state doctrine or refuse to answer on sensitive topics
AI 摘要
Aleph Alpha 发布基准测试，对阿里巴巴 Qwen、DeepSeek 和月之暗面 Kimi 等中国模型在 967 个敏感话题上的表现进行评估，称仅 17% 至 41% 的回答被评为平衡，其余重复官方立场、回避或拒答。研究还发现这种倾向会外溢到不涉及中国的问题，并指出英伟达 Nemotron Cascade 2 因训练数据含 DeepSeek 和 Qwen 生成样本而出现类似模式。文章同时提到美国也存在按意识形态塑造模型的政治努力，并称欧洲面临在两种外来价值体系间选择的问题。
正文节选
Chinese AI models parrot state doctrine or refuse to answer on sensitive topics Chinese AI models frequently toe the party line when asked politically sensitive questions, according to a study by Aleph Alpha. The company markets itself alongside Cohere as a provider of "sovereign AI" for governments, giving it a commercial interest in distinguishing its models from Chinese competitors. In a benchmark Aleph Alpha developed, the company tested models from Alibaba (Qwen), DeepSeek, and Moonshot AI