mlsanityData to 7 Oct 2026

DeepLens: Interactive Out-of-distribution Data Detection in NLP Models

arXiv 2303.01577 ↗First posted 2 Mar 2023cs.HC cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Machine Learning (ML) has been widely used in Natural Language Processing (NLP) applications. A fundamental assumption in ML is that training data and real-world data should follow a similar distribution. However, a deployed ML model may suffer from out-of-distribution (OOD) issues due to distribution shifts in the real-world data. Though many algorithms have been proposed to detect OOD data from text corpora, there is still a lack of interactive tool support for ML developers. In this work, we propose DeepLens, an interactive system that helps users detect and explore OOD issues in massive text corpora. Users can efficiently explore different OOD types in DeepLens with the help of a text clustering method. Users can also dig into a specific text by inspecting salient words highlighted through neuron activation analysis. In a within-subjects user study with 24 participants, participants using DeepLens were able to find nearly twice more types of OOD issues accurately with 22% more confidence compared with a variant of DeepLens that has no interaction or visualization support.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 39 of its 68 references that are in the map. First posted on arXiv 2 Mar 2023.

Builds on

39 of 68 references.

References · 39

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017On Calibration of Modern Neural Networkscited by 4,860
  4. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  6. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  7. 2016Concrete Problems in AI Safetycited by 1,582
  8. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  9. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  10. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  11. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  12. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
27 more
  1. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  2. 2019Designing and Interpreting Probes with Control Taskscited by 608
  3. 2020Learning under Concept Drift: A Reviewcited by 470
  4. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  5. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  6. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  7. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  8. 2018FakeNewsNet: A Data Repository with News Content, Social Context and Spatialtemporal Information for Studying Fake News on Social Mediacited by 281
  9. 2018Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shiftcited by 240
  10. 2017Multiplicative Normalizing Flows for Variational Bayesian Neural Networkscited by 157
  11. 2018Guiding Deep Learning System Testing using Surprise Adequacycited by 123
  12. 2021Can multi-label classification networks know what they don't know?cited by 100
  13. 2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
  14. 2021Types of Out-of-Distribution Texts and How to Detect Themcited by 80
  15. 2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
  16. 2019Towards neural networks that provably know when they don't knowcited by 69
  17. 2017Rasa: Open Source Language Understanding and Dialogue Managementcited by 67
  18. 2019exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Modelscited by 33
  19. 2020OoDAnalyzer: Interactive Analysis of Out-of-Distribution Samplescited by 33
  20. 2019Novelty Detection Via Blurringcited by 24
  21. 2021Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detectioncited by 23
  22. 2020Diagnosing Concept Drift with Visual Analyticscited by 14
  23. 2020ConceptExplorer: Visual Analysis of Concept Driftsin Multi-source Time-series Datacited by 12
  24. 2021A Heuristic-driven Ensemble Framework for COVID-19 Fake News Detectioncited by 10
  25. 2020ConceptScope: Organizing and Visualizing Knowledge in Documents based on Domain Ontologycited by 4
  26. 2021Contrastive Identification of Covariate Shift in Image Datacited by 4
  27. 2022Data+Shift: Supporting visual investigation of data distribution shifts by data scientistscited by 3

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 0; 2025: 2.

5 papers.

  1. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  2. 2023MSAC: Multiple Speech Attribute Control Method for Reliable Speech Emotion Recognitioncited by 4
  3. 2025RAGTrace: Understanding and Refining Retrieval-Generation Dynamics in Retrieval-Augmented Generationcited by 4
  4. 2023Mapping the Challenges of HCI: An Application and Evaluation of ChatGPT for Mining Insights at Scalecited by 2
  5. 2023ScatterUQ: Interactive Uncertainty Visualizations for Multiclass Deep Learning Problemscited by 2