研究:中国 AI 模型政治立场复杂,并非只是政府喉舌
原标题:Chinese AI models are politically complex, not just government mouthpieces, study finds
AI 摘要
AI 基准测试公司 Vals AI 研究了中国、美国及其他语言模型对数百个涉华政治问题的回答,发现中国模型的政治倾向比预期更复杂,并非一律充当政府喉舌。研究显示,提示语言对回答的政治倾向影响显著:简体中文提问比英文、俄文或西班牙文更容易得到亲政府回答,中国和美国模型都受影响,但中国模型更明显。多数中国模型很少拒答,而是有时直接采用官方立场;在智能体框架或联网搜索场景下,亲政府得分会降低。研究还发现,在翻译等日常任务中,个别模型会使用官方表述,例如 Qwen3.8 Max 将台湾译为“Taiwan, China”。
正文节选
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