Deep Papers cover image

Georgia Tech's Santosh Vempala Explains Why Language Models Hallucinate, His Research With OpenAI

Deep Papers

00:00

Audience Q: Detecting Incentives to Guess from Outputs

Parth asks about auditing models for guessing incentives and Santosh suggests mapping model confidence to abstention behavior.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app