LLMs have a strong bias against use of African American English

Quick Summary:

Feedback gets rid of overt biases but leaves subtle racism intact.

And that bias bled over into decisions the LLMs were asked to make about those who use African American English.

So some researchers decided to test whether the same might be true of LLMs.And was it ever.

---

More Pictures

---

Read Quick SummarySave Time

or

Article Details

Author / Journalist: John Timmer

Category: Technology

Markets: United States

Topics: AI LLMs Racism AI training Science Bias

Source Website Secure: Yes (HTTPS)

News Sentiment: Neutral

Fact Checked: Legitimate

Article Type: News Report

Published On: 2024-08-28 @ 15:00:59 (3 days ago)

News Timezone: GMT -5:00

News Source URL: arstechnica.com

Language: English

Article Length: 180 words

Reading Time: 1 minutes read

Sentences: 34 lines

Sentence Length: 6 words per sentence (average)

Platforms: Desktop Web, Mobile Web, iOS App, Android App

Copyright Owner: © Ars Technica

News ID: 22294469

View Article Analysis

About Ars Technica

Main Topics: Technology

Official Website: arstechnica.com

Year Established: 1998

Headquarters: United States

News Last Updated: 1 days ago

Coverage Areas: United States

Ownership: Independent Company

Publication Timezone: GMT -5:00

Content Availability: Worldwide

News Language: English

RSS Feed: Available (XML)

API Access: Available (JSON, REST)

Website Security: Secure (HTTPS)

Publisher ID: #32

Publisher Details

Frequently Asked Questions