Mystery AI Hype Theater 3000 cover image

Episode 7: There Are Now 15 Competing Evaluation Metrics (ft. Dr. Jeremy Kahn). December 12, 2022

Mystery AI Hype Theater 3000

CHAPTER

How to Evaluate Natural Language Processing in Large Language Models

Emily: Let's do it. Jeremy, you want to lead us in this? So this is a giant paper from Percy Liang and a bunch of other people. A lot of people think there are 50 authors on this paper. They've taken I think 12 or 15 different tasks. And then they tried to apply them all the way across into 12 for 15 different metrics. This is totally crazy. We need to develop one universal standard that covers everyone’s use cases. Emily: Now we have 15 competing standards for how to evaluate natural language processing. Especially in these large language models.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner