Excited to share that our paper "One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization" (joint work with @franziweeber.bsky.social, Jan Batzner and Sebastian Padó) got accepted to the main conference of #ACL 🎉
Does it matter how you prompt an LLM with a persona? Do LLMs respond differently to natural conversation history compared to names and explicit mentions? Go check out our new preprint! 👀
Vera Neplenbroek
Vera Neplenbroek
Even with identical sociodemographic info, how LLMs are given it changes downstream bias results. Our new preprint (w/ @veraneplenbroek.bsky.social, Jan Batzner & Sebastian Padó) tests cues with varying external validity across 10 personas, 4 tasks & 7 LLMs: arxiv.org/abs/2601.18572
