Study: DeepSeek repeats 30% of false news statements
Researchers found that DeepSeek-R1 repeats false claims 30 percent of the time when answering news questions, and failed to provide accurate information 83 percent of the time in testing by anti-misinformation company NewsGuard. The chatbot's outdated knowledge cut-off and programmed responses reflecting Chinese government positions reportedly limit its reliability as a news source.
What happened
NewsGuard analysis found that DeepSeek-R1 repeated false claims 30 percent of the time when presented with news-related prompts.
DeepSeek failed to provide accurate information about news and current events 83 percent of the time, placing it 10th out of 11 AI models tested by NewsGuard. The average fail rate among the top 10 leading chatbots was 62 percent.
Reported impact
Critics point out that DeepSeek should not be trusted to generate accurate, reliable or trustworthy responses to news-related questions.
Index analysis
DeepSeek's knowledge cut-off appears to be October 2023, limiting its ability to provide up-to-date information on recent events.
DeepSeek has been programmed to provide Chinese government propaganda for news-related questions, even for queries unrelated to China.
Classification
Sources and evidence
This record was researched and written by the Index, based on the following original reporting.