Pinned
Excited to share that our work on LLM personalization received the 𝑶𝒖𝒕𝒔𝒕𝒂𝒏𝒅𝒊𝒏𝒈 𝑷𝒂𝒑𝒆𝒓 𝑨𝒘𝒂𝒓𝒅 🏆 at 𝗖𝗢𝗟𝗠 𝟮𝟬𝟮𝟲 𝗟𝗶𝗳𝗲𝗹𝗼𝗻𝗴 𝗔𝗴𝗲𝗻𝘁 𝗪𝗼𝗿𝗸𝘀𝗵𝗼𝗽!
I’ll present at COLM in the oral session on Oct 9, 12:15–12:30 PM. Come say hi if you’re around!
1/ When chatbots remember something about you in “personalized” answers, does it ever feel uncomfortable, offensive, or just unnecessary?
🚨 Our paper argues these misalignments reflects a deeper issue in personalization: over-reliance on synthetic users and LLM judges.
🧵👇
