arXiv:2602.06924v3 Announce Type: replace
Abstract: Deep learning models trained to optimize average accuracy often exhibit systematic failures on particular subpopulations. In real-world settings li...
By Abinitha Gourabathina, Hyewon Jeong, Teya Bergamaschi, Marzyeh Ghassemi, Collin Stultz
arXiv:2610.01028v1 Announce Type: cross
Abstract: Machine learning models often suffer performance degradation under subpopulation shift, particularly when spurious correlations cause models to rely...
By Sung Ho Jo, Seonghwi Kim, Wonsang Yun, Minwoo Chae
The paper introduces the Forget‑Retain Alignment Gap (FRAG), a training‑free metric that evaluates how well an update to a large language model (LLM) aligns with the principle of affecting forget‑critical weights while sparing retain‑critical ones. Unlike traditional robustness predictors that rely on global weight‑space displacement, FRAG distinguishes selective from dense updates and predicts relearning robustness without running a relearning attack. The authors also propose Forget‑Retain Pruning (FRP), which leverages this principle to enhance the robustness of unlearning in LLMs.
By Yi Chen, Hanna Hsieh, Shuhong Liu, Chuanbo Hua, Zihan Ma, Kun Wang, Joo-Young Kim
arXiv:2605. 28021v2 Announce Type: replace Abstract: Out-of-distribution (OOD) detection is essential for deploying machine learning models in open-world and safety-critical scenarios, where test inputs may deviate from the training distribution and overconfident predictions on unknown samples can lead to unreliable decisions.
By Fengqiang Wan, Qing-Yuan Jiang, Fu Shen, Yang Yang
arXiv:2608.27704v1 Announce Type: new
Abstract: When machine learning classifiers are retrained, inputs correctly classified by the previous model version may be misclassified by the updated version,...
By Madhusudan Srinivasan, Namith Nishal Raphae
SAGE (Subpopulation-Aware Generative Enhancement) is a two-stage generative augmentation framework designed to mitigate spurious correlations in machine learning when group labels are unavailable. It uses cluster-derived sub-labels and class labels to fine‑tune a conditional generative model and text encoder, producing synthetic data that fills underrepresented regions and creates a balanced validation set for last‑layer reweighting. Experiments show SAGE improves worst‑group accuracy to 89.5%, 85.7%, and 79.1% on Waterbirds, CelebA, and MetaShift, outperforming existing group‑label‑free baselines by up to 7.7 percentage points.
By Yiming Luo, Rongqiang Zhao, Jie Liu