Keywords: selective prediction, open-set classification, large language models, NLP
TL;DR: We present Contrastive Novelty Learning, a method to improve open-set selective classification by generating probable novel examples with a large language model, then training a classifier for lower relative confidence on generated examples.
Abstract: In many task settings, text classification models are likely to encounter examples from novel classes on which they cannot predict correctly. Selective prediction, in which models abstain on low-confidence examples, provides a possible solution, but existing models are often overly confident on OOD examples. To remedy this overconfidence, we introduce Contrastive Novelty Learning (CNL), a two-step method that generates OOD examples representative of novel classes, then trains to decrease confidence on them. First, we generate OOD examples by prompting a large language model twice: we prompt it to enumerate novel classes relevant to the label set, then generate examples from each novel class matching the task format. Second, we train our classifier with a novel contrastive objective that encourages lower confidence on generated OOD examples than training examples. When trained with CNL, classifiers improve in their ability to detect and abstain on OOD examples over prior methods by an average of 2.3% AUAC and 5.5% AUROC across 4 NLP datasets, with no cost to in-distribution accuracy.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)