OOD Detection

3 items

RESEARCHarXiv CS.LG·17d ago

Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins

This research introduces GOEN, a novel pipeline for out-of-distribution (OOD) detection, which effectively combines multi-scale features and Mahalanobis distance. It reveals that CenterLoss surprisingly degrades OOD detection performance, with GOEN-NoCenterLoss achieving state-of-the-art results.

OOD Detection Epistemic Uncertainty Feature Engineering deep learning

RESEARCHarXiv CS.AI·17d ago

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs

This research introduces MOOD, a benchmark designed to study the detection of out-of-distribution (OOD) alignment failures in large language models (LLMs) using monitoring pipelines. It proposes combining guard models with OOD detectors to improve the generalization of safety classifiers, which often fail in OOD scenarios.

Model Monitoring OOD Detection LLMs Benchmarking

RESEARCHarXiv CS.LG·4/13/2026

Ranked Activation Shift for Post-Hoc Out-of-Distribution Detection

This research introduces a method called Ranked Activation Shift for post-hoc out-of-distribution detection. It aims to improve the identification of data samples that deviate from the training distribution.

OOD Detection neural networks deep learning machine learning