🚨 New #EMNLP2025 paper!
Do LLMs exhibit distinct behavior when the prompt looks similar to common evaluation prompts? 👀
We show that prompts that signal bias evaluation can flip the measured bias. See below ⬇️
Bufan Gao
@bufangao.bsky.social
8 followers 3 following 4 posts
Psychology PhD student @UChicago 🔗 jouisseuse.github.io