Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
How Learning Governs Unlearning across the Memorization-Generalization Spectrum
Hwiyeong Lee, Hyelim Lim, Ingyu Bang +2
While unlearning seeks to negate undesired capabilities acquired through learning, little research has examined how the way models learn shapes their subsequent unlearning. In this…
cs.LG2026
Query Lens: Interpreting Sparse Key-Value Features with Indirect Effects
Hwiyeong Lee, Ingyu Bang, Uiji Hwang +2
While sparse autoencoders provide features more interpretable than individual neurons, reliably characterizing them remains challenging. We propose Query Lens, which extends Logit…