AI language models show political biases, new research shows – Interesting Engineering
The researchers tested 14 models and found that they varied from left-wing libertarian to right-wing authoritarian on various topics.
Tag Archives: biases
Top AI chatbots have political biases, according to a study – Asia News Network
The study showed that OpenAI's ChatGPT had more left-learning and libertarian biases while Meta's LLaMA was more right-leaning and authoritarian.