most citedEM-MIAs: Enhancing Membership Inference Attacks in Large Language Models through Ensemble Modeling

1 citations · 2 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

A Layer-wise Analysis of Supervised Fine-Tuning

Qinghua Zhao, Xueling Gong, Xinyu Chen +2

While critical for alignment, Supervised Fine-Tuning (SFT) incurs the risk of catastrophic forgetting, yet the layer-wise emergence of instruction-following capabilities remains el…