AI Models Detect Racial Bias
This is a OpenAI news story, published by Live Science, that relates primarily to GPT-4 news.
OpenAI news
For more OpenAI news, you can click here:
more OpenAI newsGPT-4 news
For more GPT-4 news, you can click here:
more GPT-4 newsNews about Ai research
For more Ai research news, you can click here:
more Ai research newsLive Science news
For more news from Live Science, you can click here:
more news from Live ScienceAbout the Otherweb
Otherweb, Inc is a public benefit corporation, dedicated to improving the quality of news people consume. We are non-partisan, junk-free, and ad-free. We use artificial intelligence (AI) to remove junk from your news feed, and allow you to select the best tech news, business news, entertainment news, and much more. If you like this article about Ai research, you might also like this article about
racial biases. We are dedicated to bringing you the highest-quality news, junk-free and ad-free, about your favorite topics. Please come every day to read the latest racial bias manifests news, human biases news, news about Ai research, and other high-quality news about any topic that interests you. We are working hard to create the best news aggregator on the web, and to put you in control of your news feed - whether you choose to read the latest news through our website, our news app, or our daily newsletter - all free!
AI biasLive Science
•AI models believe racist stereotypes about African Americans that predate the Civil Rights movement — and they 'try to hide it when confronted'
72% Informative
Scientists have found that common AI models express a covert form of racism based on dialect.
The research was conducted by OpenAI 's GPT3.5 and GPT-4 , as well as Meta 's RoBERTa.
The AI models were not told the racial group of the speaker.
The findings should push companies to work harder to reduce bias in their AI models.
VR Score
84
Informative language
90
Neutral language
54
Article tone
informal
Language
English
Language complexity
65
Offensive language
possibly offensive
Hate speech
not hateful
Attention-grabbing headline
not detected
Known propaganda techniques
not detected
Time-value
long-living
External references
2
Source diversity
2
Affiliate links
2