Lost in the Middle: How Language Models Use Long Contexts
Deep Papers
Introduction
This is Lost in the Middle, how language models use context. There's really not that much known about how well these models actually use this context or even how they use it in general. And so what does the paper do to figure out how well the models are using their context and where it sometimes fails? Well, they're testing four models to open source. So that's going to be MBT 30B instruct and then long chat 13B and then two closed source models chat GPT three or not. Sorry, not chat GPT 3.5 turbo and Claude.
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.
