Carolin Holtermann

carolin-holtermann.bsky.social

24 March 2026 16:30

A huge thank you to all the amazing authors of this work!! @minhducbui.bsky.social @kaitlynzhou.bsky.social @valentinhofmann.bsky.social @a-lauscher.bsky.social

Carolin Holtermann

carolin-holtermann.bsky.social

24 March 2026 16:29

🚨 New paper alert: A new generation of LLMs can now process speech natively. This could expand access for millions excluded by text interfaces, but our research shows a cost: demographic cues in speaker voice can trigger stereotypical model responses. 🎙️⚖️ Paper: arxiv.org/abs/2603.22260

Maria Antoniak

mariaa.bsky.social

24 March 2026 16:29

Somehow I only just saw this! Congratulations @valentinhofmann.bsky.social!!

pascal

guldener.io

04 March 2026 09:50

Cool. Congrats !

Manuel Tonneau

manueltonneau.bsky.social

27 January 2026 18:17

Thanks also to @johnholbein1.bsky.social whose numerous posts on demographic probing in the social sciences inspired this work and to Matthew Kearney for the useful benchmark dataset.