Academics are expected to be at odds over a research paper that mentioned that ChatGPT presents a “significant and sizeable” political bias regarding the left side of the political spectrum, stated Cointelegraph.
Sources revealed that researchers from the United Kingdom and Brazil released the Public Choice journal on August 17, 2023. Supposedly, the paper mentions that large language models (LLMs) such as ChatGPT output text contain errors and biases that might mislead readers and have the ability to promote political biases presented by traditional media.
“We find robust evidence that ChatGPT presents a significant and systematic political bias toward the Democrats in the US, Lula in Brazil, and the Labour Party in the UK,” Victor Rangel, co-author, Cointelegraph, explained.
It is believed that Arvind Narayanan, computer science professor, Princeton, published an in-depth Medium post including a scientific critique of the report, its methodology and findings. Furthermore, the experiment did not measure bias but asked ChatGPT to roleplay as a member of a political party, Cointelegraph concluded.
(With insights from Cointelegraph)
