AP-OOD: Attention Pooling for Out-of- Distribution Detection
Claus Hofmann, Christian Huber, Bernhard Lehner, Daniel Klotz, Sepp Hochreiter, Werner Zellinger
Abstract
Out-of-distribution (OOD) detection, which maps high-dimensional data into a scalar OOD score, is critical for the reliable deployment of machine learning models. A key challenge in recent research is how to effectively leverage and aggregate token embeddings from language models to obtain the OOD score. In this work, we propose AP-OOD, a novel OOD detection method for natural language that goes beyond simple average-based aggregation by exploiting token-level information. AP-OOD is a semi-supervised approach that flexibly interpolates between unsupervised and supervised settings, enabling the use of limited auxiliary outlier data. Empirically, AP-OOD sets a new state of the art in OOD detection for text: in the unsupervised setting, it reduces the FPR95 (false positive rate at 95% true positives) from 27.77% to 5.91% on XSUM summarization, and from 75.19% to 68.13% on WMT15 En–Fr translation.
BibTeX
@inproceedings{
hofmann2026apood,
title={{AP}-{OOD}: Attention Pooling for Out-of- Distribution Detection},
author={Claus Hofmann and Christian Huber and Bernhard Lehner and Daniel Klotz and Sepp Hochreiter and Werner Zellinger},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=fEYonozhKk}
}