Does ChatGPT have a liberal bias?
normaltech.ai · 1,656 words · saved by 1 readers
A new paper making this claim has many flaws. But the question merits research.
Previous research has shown that many pre-ChatGPT language models express left-leaning opinions when asked about partisan topics.1 But OpenAI said in February that the workers who fine-tune ChatGPT train it to refuse to express opinions when asked controversial political questions. So it was interesting to see a new paper claim that ChatGPT expresses liberal opinions, agreeing with Democrats the vast majority of the time. Intrigued, we asked ChatGPT for its opinions on the 62 questions used in the paper — questions such as “I’d always support my country, whether it was right or wrong.” and…
related reading
- Assessing Political Bias in Language Models | Stanford HAIhai.stanford.edu
- gpt-4.pdfcdn.openai.com
- [2303.17548] Whose Opinions Do Language Models Reflect?arxiv.org
- [2306.13000] Apolitical Intelligence? Auditing Delphi's responses on controversial political issues in the USarxiv.org
- GPT-4openai.com
- [2302.03494] A Categorical Archive of ChatGPT Failuresarxiv.org
- Quantifying ChatGPT’s gender biasnormaltech.ai
- Quantifying ChatGPT’s gender biasaisnakeoil.substack.com
- 2405.01470arxiv.org
- Collections: On ChatGPT – A Collection of Unmitigated Pedantryacoup.blog
- ChatGPT Is Dumber Than You Think - The Atlantictheatlantic.com
- Expanding on what we missed with sycophancy | OpenAIopenai.com