EventPast event
Aleph Alpha 评测中国模型敏感议题表现
Start here
AI overview
Aleph Alpha 用自建基准测试了阿里千问（Qwen）、DeepSeek 与月之暗面（Kimi）等中国模型，覆盖天安门、台湾、新疆等 967 个敏感议题。其自研评分系统判定仅 17% 至 41% 的回答算平衡，其余为复述官方立场、回避或拒答。DeepSeek V4 Pro 拒答三分之二问题，对照的 Claude Sonnet 5 与 Mistral Small 平衡回答率分别为 70% 和 92%。
Generated by AI from reports · Updated 3 days ago
Progress timeline
Oct 4
- The DecoderAleph Alpha 研究：千问、DeepSeek、Kimi 等中国模型在敏感议题上多复述官方立场或拒答
Aleph Alpha 用自建基准测试了阿里千问（Qwen）、DeepSeek 与月之暗面（Kimi）等中国模型，覆盖天安门、台湾、新疆等 967 个敏感议题，其自研评分系统判定仅 17% 至 41% 的回答算平衡，其余为复述官方立场、回避或拒答。DeepSeek V4 Pro 拒答三分之二问题，对照的 Claude Sonnet 5 与 Mistral Small 平衡回答率分别为 70% 和 92%。研究还称 Nvidia Nemotron Cascade 2 有 17% 回答呈类似倾向，归因于其 930 万条训练样本中约 3500 条由 DeepSeek 和 Qwen 生成。
Oct 3
- 网页CBS News · Technology· DiscussionSome topics are off limits in Chinese AI, researchers find(opens the original post in a new tab)
Related discussion
Total 1 items
- Older than 72 hours · Not included in the 72-hour figures
- 网页CBS News · TechnologySome topics are off limits in Chinese AI, researchers find(opens the original post in a new tab)
Attention trend
New sources per day
- Oct 3New1 sources (1 outlets,0 accounts)
- Oct 4New1 sources (1 outlets,0 accounts)
- Oct 5New0 sources (0 outlets,0 accounts)
- Oct 6New0 sources (0 outlets,0 accounts)
- Oct 7New0 sources (0 outlets,0 accounts)
- Oct 8New0 sources (0 outlets,0 accounts)
- Oct 9New0 sources (0 outlets,0 accounts)
- Oct 10New0 sources (0 outlets,0 accounts)
- Oct 11New0 sources (0 outlets,0 accounts)
- Oct 12New0 sources (0 outlets,0 accounts)