We attempt to detect out-of-distribution (OOD) text samples though applying Topological Data Analysis (TDA) to attention maps in transformer-based language models. We evaluate our proposed TDA-based approach for out-of-distribution detection on BERT, a transformer-based language model, and compare the to a more traditional OOD approach based on BERT CLS embeddings. We found that our TDA approach outperforms the CLS embedding approach at distinguishing in-distribution data (politics and entertainment news articles from HuffPost) from far out-of-domain samples (IMDB reviews), but its effectiveness deteriorates with near out-of-domain (CNN/Dailymail) or same-domain (business news articles from HuffPost) datasets.

翻译：我们尝试通过将拓扑数据分析应用于基于Transformer语言模型的注意力图来检测分布外文本样本。我们在BERT（一种基于Transformer的语言模型）上评估了所提出的基于TDA的分布外检测方法，并将其与基于BERT CLS嵌入的传统分布外检测方法进行比较。我们发现，在区分分布内数据（来自HuffPost的政治和娱乐新闻文章）与远域外样本（IMDB评论）时，我们的TDA方法优于CLS嵌入方法，但在近域外（CNN/Dailymail）或同域（来自HuffPost的商业新闻文章）数据集上，其有效性会下降。