Showing 2025Show all
2 papers · 1 filter
cs.CL2025
Randomized Masked Finetuning: An Efficient Way to Mitigate Memorization of PIIs in LLMs
Kunj Joshi, David A. Smith
The current literature on memorization in Natural Language Models, especially Large Language Models (LLMs), poses severe security and privacy risks, as models tend to memorize pers…
cs.LG2025
Post-Norm can Resharpen Attention
Pál Zsámboki, Benjamin Levi, David Ansel Josef Smith +4
Length Generalization is the essential capacity of autonomous agents to perform tasks in longer contexts than those encountered during training. To systematically study this feat,…