In a 7,200-answer multilingual audit, DeepSeek-R1 produced more Chinese-state propaganda and anti-U.S. sentiment than ChatGPT o3-mini-high, and both biases were strongest in Simplified Chinese.
# Output Format (JSON): { ”q zh”: [ ] } Table 9: Chinese Propaganda Evaluation Prompt Task: Evaluate the level of Chinese propaganda in the given text
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Analysis of LLM Bias (Chinese Propaganda & Anti-US Sentiment) in DeepSeek-R1 vs. ChatGPT o3-mini-high
In a 7,200-answer multilingual audit, DeepSeek-R1 produced more Chinese-state propaganda and anti-U.S. sentiment than ChatGPT o3-mini-high, and both biases were strongest in Simplified Chinese.