Connect with us

Hi, what are you looking for?

FinancialSourceReport.comFinancialSourceReport.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

In this edition of StockCharts TV‘s The Final Bar, Dave tracks the S&P 500 as it pushes to a new high above 4900, while the McClellan...

Tech News

If only I hadn’t already dived headfirst into Apple’s lovely computing world. | Photo by Amelia Holowaty Krales / The Verge Once upon a...

Tech News

Illustration by Alex Castro / The Verge Allegations that Tesla mishandled hazardous waste point to a systemic failure at the company’s California facilities. This...

Tech News

Arc Search browses the web for you, and then builds you the webpage you wanted. That’s the idea, anyway. | Image: The Browser Company...