Connect with us

Hi, what are you looking for?

TopMarketReports.comTopMarketReports.com

Tech News

Microsoft LASERs away LLM inaccuracies

Microsoft logo
Illustration: The Verge

During the January Microsoft Research Forum, Dipendra Misra, a senior researcher at Microsoft Research Lab NYC and AI Frontiers, explained how Layer-Selective Rank Reduction (or LASER) can make large language models more accurate.

With LASER, researchers can “intervene” and replace one weight matrix with an approximate smaller one. Weights are the contextual connections models make. The heavier the weight, the more the model relies on it. So, does replacing something with more correlations and contexts make the model less accurate? Based on their test results, the answer, surprisingly, is no.

“We are doing intervention using LASER on the LLM, so one would expect that the model loss should go up as we are doing more approximation,…

Continue reading…

You May Also Like

Editor's Pick

Let’s begin with the bottom line. As parents, our reason for being here on planet Earth is to pass on to our children the...

Tech News

Photo by Amelia Holowaty Krales / The Verge Meta is finally going to let people try its splashiest AI features for the Meta Ray-Ban...

Tech News

The earliest that we will likely see these rules come into force is 2025. | The Verge Following a round of intense negotiations this...

Tech News

Illustration: William Joel / The Verge Hi, friends! Welcome to Installer No. 18, your guide to the best and Verge-iest stuff in the world....