mlsanityData to 14 Oct 2026

PnPOOD : Out-Of-Distribution Detection for Text Classification via Plug andPlay Data Augmentation

arXiv 2111.00506 ↗First posted 31 Oct 2021cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

While Out-of-distribution (OOD) detection has been well explored in computer vision, there have been relatively few prior attempts in OOD detection for NLP classification. In this paper we argue that these prior attempts do not fully address the OOD problem and may suffer from data leakage and poor calibration of the resulting models. We present PnPOOD, a data augmentation technique to perform OOD detection via out-of-domain sample generation using the recently proposed Plug and Play Language Model (Dathathri et al., 2020). Our method generates high quality discriminative samples close to the class boundaries, resulting in accurate OOD detection at test time. We demonstrate that our model outperforms prior models on OOD sample detection, and exhibits lower calibration error on the 20 newsgroup text and Stanford Sentiment Treebank dataset (Lang, 1995; Socheret al., 2013). We further highlight an important data leakage issue with datasets used in prior attempts at OOD detection, and share results on a new dataset for OOD detection that does not suffer from the same problem.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 21 of its 28 references that are in the map. First posted on arXiv 31 Oct 2021.

Builds on

21 of 28 references.

References · 21

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2017On Calibration of Modern Neural Networkscited by 4,960
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  6. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  8. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  9. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  10. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  11. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  12. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 799
9 more
  1. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  2. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  3. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  4. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 386
  5. 2019Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibrationcited by 364
  6. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  7. 2016Multi30K: Multilingual English-German Image Descriptionscited by 250
  8. 2019On-manifold Adversarial Data Augmentation Improves Uncertainty Calibrationcited by 18
  9. 2013Complexity of Word Collocation Networks: A Preliminary Structural Analysiscited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 5; 2024: 1; 2025: 1; 2026: 2.

12 papers.

  1. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 197
  2. 2023A Survey on Out-of-Distribution Detection in NLPcited by 31
  3. 2023Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detectioncited by 29
  4. 2022OOD-DiskANN: Efficient and Scalable Graph ANNS for Out-of-Distribution Queriescited by 15
  5. 2023Classical Out-of-Distribution Detection Methods Benchmark in Text Classification Taskscited by 5
  6. 2025Prompting without Panic: Attribute-aware, Zero-shot, Test-Time Calibrationcited by 2
  7. 2023Semantic Role Labeling Guided Out-of-distribution Detectioncited by 1
  8. 2022Constraining Representations Yields Models That Know What They Don't Knowcited by 0
  9. 2023BED: Bi-Encoder-Based Detectors for Out-of-Distribution Detectioncited by 0
  10. 2024Tree-based Ensemble Learning for Out-of-distribution Detectioncited by 0
  11. 2026Enhancing Deep Neural Network Reliability with Refinement and Calibrationcited by 0
  12. 2026Few-Shot Out of Domain Intent Detection with Covariance Corrected Mahalanobis Distancecited by 0