mlsanityData to 7 Oct 2026

Towards Textual Out-of-Domain Detection without In-Domain Labels

arXiv 2203.11396 ↗First posted 22 Mar 2022cs.CL cs.AI cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

In many real-world settings, machine learning models need to identify user inputs that are out-of-domain (OOD) so as to avoid performing wrong actions. This work focuses on a challenging case of OOD detection, where no labels for in-domain data are accessible (e.g., no intent labels for the intent classification task). To this end, we first evaluate different language model based approaches that predict likelihood for a sequence of tokens. Furthermore, we propose a novel representation learning based method by combining unsupervised clustering and contrastive learning so that better data representations for OOD detection can be learned. Through extensive experiments, we demonstrate that this method can significantly outperform likelihood-based methods and can be even competitive to the state-of-the-art supervised approaches with label information.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 33 of its 39 references that are in the map. First posted on arXiv 22 Mar 2022.

Builds on

33 of 39 references.

References · 33

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  8. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  9. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  10. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  11. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  12. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 763
21 more
  1. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  2. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  3. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  4. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  5. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 376
  6. 2020Learning and Evaluating Representations for Deep One-class Classificationcited by 133
  7. 2018Cross-Lingual Transfer Learning for Multilingual Task Oriented Dialogcited by 124
  8. 2017DOC: Deep Open Classification of Text Documentscited by 109
  9. 2021Supporting Clustering with Contrastive Learningcited by 90
  10. 2021Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detectioncited by 67
  11. 2019Deep Unknown Intent Detection with Margin Losscited by 66
  12. 2019Out-of-domain Detection for Natural Language Understanding in Dialog Systemscited by 62
  13. 2018Zero-shot User Intent Detection via Capsule Neural Networkscited by 54
  14. 2020Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inferencecited by 47
  15. 2019Out-of-Domain Detection for Low-Resource Text Classification Taskscited by 36
  16. 2017Self-Taught Convolutional Neural Networks for Short Text Clusteringcited by 34
  17. 2019Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection In Task Oriented Dialogcited by 33
  18. 2020Language Model is All You Need: Natural Language Understanding as Question Answeringcited by 29
  19. 2020Why is the Mahalanobis Distance Effective for Anomaly Detection?cited by 28
  20. 2018WAIC, but Why? Generative Ensembles for Robust Anomaly Detectioncited by 25
  21. 2021Towards Zero and Few-shot Knowledge-seeking Turn Detection in Task-orientated Dialogue Systemscited by 3

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 4; 2024: 2; 2025: 4.

14 papers.

Sort:

By area:

  1. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  2. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  3. 2023Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detectioncited by 29
  4. 2022Estimating Soft Labels for Out-of-Domain Intent Detectioncited by 11
  5. 2022Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Textcited by 11
  6. 2024Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detectorcited by 11
  7. 2023Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contextscited by 6
  8. 2025SimLabel: Consistency-Guided OOD Detection with Pretrained Vision-Language Modelscited by 5
  9. 2025Deep Learning Approaches for Multimodal Intent Recognition: A Surveycited by 5
  10. 2025Knowledge Regularized Negative Feature Tuning of Vision-Language Models for Out-of-Distribution Detectioncited by 4
  11. 2023A Hybrid Architecture for Out of Domain Intent Detection and Intent Discoverycited by 2
  12. 2023Estimating Semantic Similarity between In-Domain and Out-of-Domain Samplescited by 1
2 more
  1. 2024A Comprehensive Review of Machine Learning Advances on Data Change: A Cross-Field Perspectivecited by 1
  2. 2025GLIP-OOD: Zero-Shot Graph OOD Detection with Graph Foundation Modelcited by 1