Unsupervised Layer-wise Score Aggregation for Textual OOD Detection

Abstract

Out-of-distribution (OOD) detection is a rapidly growing field due to new robustness and security requirements driven by an increased number of AI-based systems. Existing OOD textual detectors often rely on anomaly scores (e.g., Mahalanobis distance) computed on the embedding output of the last layer of the encoder. In this work, we observe that OOD detection performance varies greatly depending on the task and layer output. More importantly, we show that the usual choice (the last layer) is rarely the best one for OOD detection and that far better results can be achieved provided that an oracle selects the best layer. To leverage this observation, we propose a data-driven, unsupervised method to combine layer-wise anomaly scores. In addition, we extend classical textual OOD benchmarks by including classification tasks with a greater number of classes (up to 77), which reflects more realistic settings. On this augmented benchmark, we show that the proposed post-aggregation methods achieve robust and consistent results comparable to using the best layer according to an oracle while removing manual feature selection altogether.

Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models

“…This further demonstrates that the transductive loss can be useful in few-shot NLP. In the future, we would like to explore the application of transductive inference to other NLP tasks such as sequence generation (Pichler et al, 2022;Colombo et al, 2019Colombo et al, , 2021d and classification tasks (Chapuis et al, 2020;Colombo et al, 2022d,b;Himmi et al, 2023) as well as NLG evaluation (Colombo et al, 2021e, 2022c(Colombo et al, 2021e, , 2021c and Safe AI Picot et al, 2022a,b;Darrin et al, 2022Darrin et al, , 2023…”