2 papers
cs.LG2026
A Spectral Theory of Grokking: Weight Decay induces Feature Learning
Lenz Pracher, Pascal de Jong, Oskar Lieshaus +2
In grokking an early fit to the training data separates from a much later improvement in generalization. During this delay, training can move from a fixed neural tangent kernel (NT…
cs.CY2026
Strategies of cooperation and defection in five large language models
Saptarshi Pal, Abhishek Mallela, Christian Hilbe +5
Large language models (LLMs) are increasingly deployed to support human decision-making. This use of LLMs has concerning implications, especially when their prescriptions affect th…