AP-OOD: Attention Pooling for Out-of- Distribution Detection
Silicon Austria Labs GmbH · Silicon Austria Labs, JKU LIT SAL eSPML Lab · Interdisciplinary Transformation University Austria · LIT AI Lab, Johannes Kepler University Linz AND Institute of Advanced Reserch in Artificial Intelligence · RICAM, Austrian Academy of Sciences
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
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.