Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
When Attention Collapses: How Degenerate Layers in LLMs Enable Smaller, Stronger Models
Sunny Sanyal, Ravid Shwartz-Ziv, Alexandros G. Dimakis +1
Large Language Models (LLMs) are known for their performance, but we uncover a significant structural inefficiency: a phenomenon we term attention collapse. In many pre-trained dec…
cs.CL2024
Language models scale reliably with over-training and on downstream tasks
Samir Yitzhak Gadre, Georgios Smyrnis, Vaishaal Shankar +22
Scaling laws are useful guides for derisking expensive training runs, as they predict performance of large models using cheaper, small-scale experiments. However, there remain gaps…