Deep Papers cover image

Lost in the Middle: How Language Models Use Long Contexts

Deep Papers

CHAPTER

The Decline of Multi-Document Accuracy

When the total number of documents that we're retrieving is increasing, our accuracy is going down and really just seeing this U. So meaning that all this context in the middle, it's not really helping the LLM,. It's not able to see the answer that's in that document. That was for the multi-document accuracy. And moving on to the JSON task, they noticed that cloud performed really particularly on all the input lengths while the other models struggled. We've heard a lot about OpenAI, maybe on graphics, going to come in here and sweep us off with a cloud. But let's get to here it is.

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