mlsanityData to 14 Oct 2026

Estimating Soft Labels for Out-of-Domain Intent Detection

arXiv 2211.05561 ↗First posted 10 Nov 2022cs.CL cs.AI cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Out-of-Domain (OOD) intent detection is important for practical dialog systems. To alleviate the issue of lacking OOD training samples, some works propose synthesizing pseudo OOD samples and directly assigning one-hot OOD labels to these pseudo samples. However, these one-hot labels introduce noises to the training process because some hard pseudo OOD samples may coincide with In-Domain (IND) intents. In this paper, we propose an adaptive soft pseudo labeling (ASoul) method that can estimate soft labels for pseudo OOD samples when training OOD detectors. Semantic connections between pseudo OOD samples and IND intents are captured using an embedding graph. A co-training framework is further introduced to produce resulting soft labels following the smoothness assumption, i.e., close samples are likely to have similar labels. Extensive experiments on three benchmark datasets show that ASoul consistently improves the OOD detection performance and outperforms various competitive baselines.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 60 of its 75 references that are in the map. First posted on arXiv 10 Nov 2022.

Builds on

60 of 75 references.

References · 60

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  8. 2020Supervised Contrastive Learningcited by 2,829
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  10. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  11. 2020Knowledge Distillation: A Surveycited by 1,603
  12. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
38 more
  1. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  2. 2019When Does Label Smoothing Help?cited by 988
  3. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  4. 2015Towards Open Set Deep Networkscited by 538
  5. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  6. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 433
  7. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  8. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 386
  9. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  10. 2018Recent Advances in Open Set Recognition: A Surveycited by 310
  11. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  12. 2020Supervised Contrastive Learning for Pre-trained Language Model Fine-tuningcited by 276
  13. 2020CoMatch: Semi-supervised Learning with Contrastive Graph Regularizationcited by 167
  14. 2021Learning Placeholders for Open-Set Recognitioncited by 121
  15. 2017DOC: Deep Open Classification of Text Documentscited by 109
  16. 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
  17. 2020SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustnesscited by 96
  18. 2020A Large-Scale Chinese Short-Text Conversation Datasetcited by 77
  19. 2019A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Datacited by 74
  20. 2021Contrastive Out-of-Distribution Detection for Pretrained Transformerscited by 71
  21. 2021Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detectioncited by 70
  22. 2019Deep Unknown Intent Detection with Margin Losscited by 66
  23. 2019Out-of-domain Detection for Natural Language Understanding in Dialog Systemscited by 62
  24. 2020Deep Open Intent Classification with Adaptive Decision Boundarycited by 56
  25. 2017Smooth Neighbors on Teacher Graphs for Semi-supervised Learningcited by 48
  26. 2021Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learningcited by 42
  27. 2021Out-of-Scope Intent Detection with Self-Supervision and Discriminative Trainingcited by 42
  28. 2019Out-of-Domain Detection for Low-Resource Text Classification Taskscited by 36
  29. 2021EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Trainingcited by 34
  30. 2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generationcited by 34
  31. 2019Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection In Task Oriented Dialogcited by 33
  32. 2021Unsupervised Out-of-Domain Detection via Pre-trained Transformerscited by 31
  33. 2021MMChat: Multi-Modal Chat Dataset on Social Mediacited by 30
  34. 2022Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsingcited by 30
  35. 2022SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understandingcited by 28
  36. 2021Diversifying Dialog Generation via Adaptive Label Smoothingcited by 25
  37. 2021Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLUcited by 22
  38. 2020Dialogue Distillation: Open-Domain Dialogue Augmentation Using Unpaired Datacited by 20

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 6; 2024: 3; 2025: 2.

11 papers.

  1. 2024On Large Language Model Continual Unlearningcited by 52
  2. 2023A Survey on Out-of-Distribution Detection in NLPcited by 31
  3. 2023Exploring Large Language Models for Multi-Modal Out-of-Distribution Detectioncited by 13
  4. 2023Long-Tailed Question Answering in an Open Worldcited by 7
  5. 2023Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contextscited by 6
  6. 2023Domain Incremental Lifelong Learning in an Open Worldcited by 5
  7. 2024Out-of-Distribution Detection through Soft Clustering with Non-Negative Kernel Regressioncited by 3
  8. 2025LANID: LLM-assisted New Intent Discoverycited by 3
  9. 2024How Out-of-Distribution Detection Learning Theory Enhances Transformer: Learnability and Reliabilitycited by 1
  10. 2023Unified Uncertainty Calibrationcited by 0
  11. 2025Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Spacecited by 0