Paper Image

Examining biases in vision-language chatbots

Published on:

8 February 2024

Primary Category:

Computers and Society

Paper Authors:

Kathleen C. Fraser,

Svetlana Kiritchenko

Bullets

Key Details

New dataset of AI-generated 'parallel' images varying only in gender and race

Images cover everyday scenarios like occupations and activities

Queried vision-language chatbots exhibit gender and racial bias

Bias manifests in occupation stereotypes and crime associations

Explore the topics in this paper

AI generated summary

Examining biases in vision-language chatbots

The paper presents a new dataset of AI-generated images that are identical except for the gender and race of the person depicted. By querying vision-language chatbots with these images, the authors uncover differences in how the chatbots describe people based on perceived gender and race.

Answers from this paper

Comments

No comments yet, be the first to start the conversation...

Sign up to comment on this paper

Sign Up