Sarah Dryhurst
@sarahdryhurst.bsky.social
Assistant Professor in risk perception and risk communication at UCL + Research Affiliate at CSER Cambridge. Runner, podcast obsessive and music nerd!
Reposted by Sarah Dryhurst
1/9 🧵 New paper alert (now in Nature Computational Science)!
As polarisation continues to shape our world, we asked: Do social and political biases transfer to our AI? I.e. do LLMs show ingroup and outgroup bias?
www.nature.com/articles/s43...
As polarisation continues to shape our world, we asked: Do social and political biases transfer to our AI? I.e. do LLMs show ingroup and outgroup bias?
www.nature.com/articles/s43...
Generative language models exhibit social identity biases - Nature Computational Science
Researchers show that large language models exhibit social identity biases similar to humans, having favoritism toward ingroups and hostility toward outgroups. These biases persist across models, trai...
www.nature.com
December 12, 2024 at 10:39 PM
1/9 🧵 New paper alert (now in Nature Computational Science)!
As polarisation continues to shape our world, we asked: Do social and political biases transfer to our AI? I.e. do LLMs show ingroup and outgroup bias?
www.nature.com/articles/s43...
As polarisation continues to shape our world, we asked: Do social and political biases transfer to our AI? I.e. do LLMs show ingroup and outgroup bias?
www.nature.com/articles/s43...