Aleph Alpha 研究：中国 AI 模型在敏感问题上倾向官方立场或拒答
Chinese AI models parrot state doctrine or refuse to answer on sensitive topics
德国公司 Aleph Alpha 测了中国模型的敏感话题回答，均衡率只有 17%-41%，不过它自己也卖"主权 AI"，看时留个心眼。
Aleph Alpha 发布研究，测试中国 AI 模型对政治敏感问题的回答。结果显示，仅 17% 到 41% 的回答被评为立场均衡，其余回答要么复述官方立场，要么直接拒绝作答。需要注意，Aleph Alpha 本身向政府出售"主权 AI"方案，与中国的模型存在商业竞争关系，研究立场可能有偏向。
Chinese AI models parrot state doctrine or refuse to answer on sensitive topics
Chinese AI models often follow the party line on politically sensitive questions, according to an Aleph Alpha study that rated only 17 to 41 percent of answers as balanced. Aleph Alpha sells "sovereign AI" to governments, giving it a commercial interest in distinguishing its models from Chinese competitors. The article Chinese AI models parrot state doctrine or refuse to answer on sensitive topics appeared first on The Decoder .
