Microsoft LASERs away LLM inaccuracies

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 …

explained frontiers illustration lab language language models large language large language models lasers layer llm matrix microsoft microsoft research nyc research researcher researchers weight matrix