Yoav Artzi: Training from scratch, not post-hoc RAG augmentation

yoavartzi · x · 2026-08-20

Yoav Artzi clarifies that the approach is not post-hoc RAG augmentation but involves training from scratch to externalize knowledge. It offers a more expressive retriever and better scalable data preprocessing compared to the first LMLM.

Related event: Researchers Unveil New Paradigm: Training from Scratch with Externalized Knowledge(2 posts)→

Original post →

More from Research

Research channel →