mlsanityData to 7 Oct 2026

Explaining Predictions of Non-Linear Classifiers in NLP

arXiv 1606.07298 ↗First posted 23 Jun 2016cs.CL cs.IR cs.LGcited by 37

Not on the map. Why?

Abstract (arXiv)

Layer-wise relevance propagation (LRP) is a recently proposed technique for explaining predictions of complex non-linear classifiers in terms of input variables. In this paper, we apply LRP for the first time to natural language processing (NLP). More precisely, we use it to explain the predictions of a convolutional neural network (CNN) trained on a topic categorization task. Our analysis highlights which words are relevant for a specific prediction of the CNN. We compare our technique to standard sensitivity analysis, both qualitatively and quantitatively, using a "word deleting" perturbation experiment, a PCA analysis, and various visualizations. All experiments validate the suitability of LRP for explaining the CNN predictions, which is also in line with results reported in recent image classification studies.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Jun 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 8; 2023: 6; 2024: 4; 2025: 2; 2026: 4.

37 papers.

Sort:

By area:

  1. 2022CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Taskcited by 205
  2. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 129
  3. 2021On Guaranteed Optimal Robust Explanations for NLP Modelscited by 54
  4. 2021Explanation-Based Human Debugging of NLP Models: A Surveycited by 53
  5. 2025Walk the Talk? Measuring the Faithfulness of Large Language Model Explanationscited by 44
  6. 2021Evaluating Saliency Methods for Neural Language Modelscited by 37
  7. 2021Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classificationcited by 29
  8. 2024Mechanistic?cited by 25
  9. 2022Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze?cited by 20
  10. 2021Interpreting Deep Learning Models in Natural Language Processing: A Reviewcited by 19
  11. 2021On the Lack of Robust Interpretability of Neural Text Classifierscited by 17
  12. 2021Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Saliencecited by 16
25 more
  1. 2022Towards Explainable Evaluation Metrics for Natural Language Generationcited by 15
  2. 2023Building a Llama2-finetuned LLM for Odia Language Utilizing Domain Knowledge Instruction Setcited by 12
  3. 2021Thermostat: A Large Collection of NLP Model Explanations and Analysis Toolscited by 11
  4. 2021Flexible Instance-Specific Rationalization of NLP Modelscited by 10
  5. 2025A Close Look at Decomposition-based XAI-Methods for Transformer Language Modelscited by 10
  6. 2022Interpretation of Black Box NLP Models: A Surveycited by 9
  7. 2022A Unified Study of Machine Learning Explanation Evaluation Metricscited by 6
  8. 2021XPROAX-Local explanations for text classification with progressive neighborhood approximationcited by 5
  9. 2023A New Perspective on Evaluation Methods for Explainable Artificial Intelligence (XAI)cited by 5
  10. 2021Rationale production to support clinical decision-makingcited by 3
  11. 2021More Than Words: Towards Better Quality Interpretations of Text Classifierscited by 2
  12. 2022Understanding Text Classification Data and Models Using Aggregated Input Saliencecited by 2
  13. 2023PROMINET: Prototype-based Multi-View Network for Interpretable Email Response Predictioncited by 2
  14. 2024An Evaluation of Explanation Methods for Black-Box Detectors of Machine-Generated Textcited by 2
  15. 2022Argumentative Explanations for Pattern-Based Text Classifierscited by 1
  16. 2023Explaining text classifiers through progressive neighborhood approximation with realistic samplescited by 1
  17. 2023Robust Infidelity: When Faithfulness Measures on Masked Language Models Are Misleadingcited by 1
  18. 2023Explaining the Decisions of Deep Policy Networks for Robotic Manipulationscited by 1
  19. 2024InfFeed: Influence Functions as a Feedback to Improve the Performance of Subjective Taskscited by 1
  20. 2021Geo-Context Aware Study of Vision-Based Autonomous Driving Models and Spatial Video Datacited by 0
  21. 2024NLPGuard: A Framework for Mitigating the Use of Protected Attributes by NLP Classifierscited by 0
  22. 2026Legal Experts Disagree With Rationale Extraction Techniques for Explaining ECtHR Case Outcome Classificationcited by 0
  23. 2026Evaluating Explainable AI Attribution Methods in Neural Machine Translation via Attention-Guided Knowledge Distillationcited by 0
  24. 2026Principal Prototype Analysis on Manifold for Interpretable Reinforcement Learningcited by 0
  25. 2026The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Playcited by 0