News for hackers. Stuff that matters.
Re:Retrieval Meets Long Context Large Language Models by Jimmc414 on Wednesday October 04, 2023 @10:42PM (#37774338)
The main findings are:

Retrieval-augmentation can significantly boost the performance of both 4K short context LLMs and 16K/32K long context LLMs.

The 4K context LLMs with simple retrieval-augmentation can perform comparable to 16K long context LLMs, while being more efficient at inference.

After context window extension and retrieval-augmentation, the best model LLaMA2-70B-32k-ret can outperform GPT-3.5-turbo-16k and Davinci003 in terms of average score on a suit of downstream tasks with informative queries.

There are no comments on this comment yet.