mlsanityData to 13 Oct 2026

Distribution Calibration for Out-of-Domain Detection with Bayesian Approximation

arXiv 2209.06612 ↗First posted 14 Sep 2022cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

Out-of-Domain (OOD) detection is a key component in a task-oriented dialog system, which aims to identify whether a query falls outside the predefined supported intent set. Previous softmax-based detection algorithms are proved to be overconfident for OOD samples. In this paper, we analyze overconfident OOD comes from distribution uncertainty due to the mismatch between the training and test distributions, which makes the model can't confidently make predictions thus probably causing abnormal softmax scores. We propose a Bayesian OOD detection framework to calibrate distribution uncertainty using Monte-Carlo Dropout. Our method is flexible and easily pluggable into existing softmax-based baselines and gains 33.33% OOD F1 improvements with increasing only 0.41% inference time compared to MSP. Further analyses show the effectiveness of Bayesian learning for OOD detection.

Key facts. Cited by 7 papers in the map (data through 13 Oct 2026). Builds on 13 of its 23 references that are in the map. First posted on arXiv 14 Sep 2022.

Builds on

13 of 23 references.

References · 13

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  3. 2017On Calibration of Modern Neural Networkscited by 4,902
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,430
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,371
  6. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,327
  7. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  8. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 381
  9. 2018From Eliza to XiaoIce: Challenges and Opportunities with Social Chatbotscited by 85
  10. 2019Deep Unknown Intent Detection with Margin Losscited by 66
  11. 2019Out-of-domain Detection for Natural Language Understanding in Dialog Systemscited by 62
  12. 2021Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learningcited by 42
1 more
  1. 2017Chat Detection in an Intelligent Assistant: Combining Task-oriented and Non-task-oriented Spoken Dialogue Systemscited by 8

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 1; 2025: 1.

7 papers.

  1. 2024Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detectioncited by 14
  2. 2023Continual Generalized Intent Discovery: Marching Towards Dynamic and Open-world Intent Recognitioncited by 5
  3. 2025Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Modelscited by 4
  4. 2023SELFOOD: Self-Supervised Out-Of-Distribution Detection via Learning to Rankcited by 3
  5. 2023APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detectioncited by 3
  6. 2022Disentangling Confidence Score Distribution for Out-of-Domain Intent Detection with Energy-Based Learningcited by 2
  7. 2022Rethinking and Recomputing the Value of Machine Learning Modelscited by 1