A new report revealed that the large language model ChatGPT has a “significant and systematic political bias” toward the left, the New York Post reported.
Researchers at the University of East Anglia in Norwich, United Kingdom, found that the popular artificial intelligence-powered system is exhibiting a bias toward particular political leanings.
The report, “More human than human: measuring ChatGPT political bias,” found that, despite the company ensuring the system is impartial, its responses to certain political questions leaned in favor of the Democratic Party in the United States, Brazil’s President Luiz Inácio Lula da Silva, and the Labour Party in the United Kingdom.
Researchers noted that bias in LLMs and other AI systems could have “adverse political and electoral consequences similar to bias from traditional and social media.” They also added that political bias can be more challenging to detect than gender or racial bias.
In order to determine and measure political leaning with the ChatGPT system, researchers conducted a test in which they requested that the AI program impersonate individuals on various sides of the political spectrum while answering ideological questions. The researchers then compared the…
