Out-of-distribution (OOD) detection plays a crucial role in ensuring the safety and reliability of deep neural networks in various applications. While there has been a growing focus on OOD detection in visual data, the field of textual OOD detection has received less attention. Only a few attempts have been made to directly apply general OOD detection methods to natural language processing (NLP) tasks, without adequately considering the characteristics of textual data. In this paper, we delve into textual OOD detection with Transformers. We first identify a key problem prevalent in existing OOD detection methods: the biased representation learned through the maximization of the conditional likelihood $p(y\mid x)$ can potentially result in subpar performance. We then propose a novel variational inference framework for OOD detection (VI-OOD), which maximizes the likelihood of the joint distribution $p(x, y)$ instead of $p(y\mid x)$. VI-OOD is tailored for textual OOD detection by efficiently exploiting the representations of pre-trained Transformers. Through comprehensive experiments on various text classification tasks, VI-OOD demonstrates its effectiveness and wide applicability. Our code has been released at \url{https://github.com/liam0949/LLM-OOD}.

使用Transformers，本文提出了一种针对文本型OOD检测的新颖变分推断框架（VI-OOD），通过有效利用预训练Transformers的表示，最大化联合分布$p(x, y)$的似然度，从而解决了现有OOD检测方法中出现的问题。通过对多个文本分类任务的广泛实验，VI-OOD展示了其高效性和广泛适用性。

VI-OOD：文本外分布检测的统一表示学习框架