mlsanityData to 14 Oct 2026

Few-Shot Out of Domain Intent Detection with Covariance Corrected Mahalanobis Distance

arXiv 2609.00961 ↗First posted 1 Sep 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Conversational agents like chatbots and voice assistants are trained to understand and respond to user intents. On encountering an utterance with an intent different from the ones they have been trained on, these agents are expected to classify the intent as `unknown' or `out of domain'. This problem is known as out of domain (OOD) intent detection. Podolskiy et al. (2021), showed that Mahalanobis distance can be used effectively for identifying OOD intents, outperforming competing approaches. However, their method fails to outperform the baselines in the practically important few-shot setting. In this paper we analyze the reason for low performance and propose a covariance corrected Mahalanobis distance for detecting out-of-domain intents.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 25 references that are in the map. First posted on arXiv 1 Sep 2026.

Builds on

15 of 25 references.

References · 15

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  2. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  3. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  4. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  5. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  6. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 386
  7. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 377
  8. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  9. 2017A Survey on Dialogue Systems: Recent Advances and New Frontierscited by 162
  10. 2018Cross-Lingual Transfer Learning for Multilingual Task Oriented Dialogcited by 125
  11. 2021Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detectioncited by 70
  12. 2019Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection In Task Oriented Dialogcited by 33
3 more
  1. 2021No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasetscited by 31
  2. 2021GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentationcited by 20
  3. 2021PnPOOD : Out-Of-Distribution Detection for Text Classification via Plug andPlay Data Augmentationcited by 12

Built on by

Not cited yet.