Vals Study Reveals Political Leanings in Chinese AI Models
Current overview (not historical)
A Vals study testing Chinese AI models' alignment with government stances found generally low overall government tendency, but massive individual differences. GLM-5.3 Flash explicitly confirmed China's human rights record, while Kimi K3 redefined Xinjiang camps as vocational training centers. When prompted for Chinese mainland companies, some models leaned toward government positions; Qwen3.8 Max rendered Taiwan as "Taiwan, China," implying sovereignty claims.
Written with AI from the reporting · updated 11/1/2026
Expand the detailed fact route and sources
Story route
A station-by-station route from the first public evidence onward; every station carries its own evidence and uncertainty.
- 1Unclassified fact stationNov 1, 00:00recorded Nov 1, 20:37single sourcerevised
Vals研究揭示中文AI模型政治倾向差异
Read original source ↗ The DecoderReplay this moment in the explorerEvidence & revisions · 1 source records
- Subject：
- Vals
- Action：
- 发布政治倾向评估研究报告
- Object：
- 测试的AI模型
- Occurred (fact side)：
- Nov 1, 00:00
- Published (valid side)：
- Nov 1, 20:33
- First seen (known side)：
- Nov 1, 20:37
Fact stationSingle source · one-sided claimRevisedCopy may have been revised later; time replay is bounded. Layer labels group reading only, not causation between layers.
Uncertainty marks flag where to check the sources; they are not proven causation.
Report timeline
Explore every side through dated source reports.
- The DecoderRelated fact: single sourceSource report revisedVals study finds Chinese AI models show political complexity, not just government alignment
Report first recorded Nov 1, 20:37
Vals study tested multiple Chinese and non-Chinese models' alignment with Chinese government positions. The research found that Chinese models overall show lower pro-government lean than expected, with significant variation between individual models. Language has a strong effect on political slant: responses in Simplified Chinese were more pro-government than those in English, Russian, or Spanish. Some models, like GLM-5.3 Flash, explicitly confirmed documented human rights violations, while others, like Kimi K3, redefined Xinjiang detention camps as vocational training centers. The study also found that system prompts indicating mainland China usage increased pro-government responses, and that models sometimes adopted official positions rather than refusing to answer sensitive questions.
Read original source ↗
Event activity trend
- Latest comparable
- 3
- Comparable peak
- 10Nov 1, 21:00
- 24h change
- -51%
The chart compares consistently observed participants only. Hover or tap to inspect each hour; use arrow keys to move between observations.
Event discussion
Reader opinions are hosted on GitHub Discussions; posting requires a GitHub account. Comments are not verified facts.