mlsanityData to 7 Oct 2026

Explaining Recurrent Neural Network Predictions in Sentiment Analysis

arXiv 1706.07206 ↗First posted 22 Jun 2017cs.CL cs.AI cs.NEcited by 87

Not on the map. Why?

Abstract (arXiv)

Recently, a technique called Layer-wise Relevance Propagation (LRP) was shown to deliver insightful explanations in the form of input space relevances for understanding feed-forward neural network classification decisions. In the present work, we extend the usage of LRP to recurrent neural networks. We propose a specific propagation rule applicable to multiplicative connections as they arise in recurrent network architectures such as LSTMs and GRUs. We apply our technique to a word-based bi-directional LSTM model on a five-class sentiment prediction task, and evaluate the resulting LRP relevances both qualitatively and quantitatively, obtaining better results than a gradient-based related method which was used in previous work.

Key facts. Cited by 87 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 26; 2022: 18; 2023: 15; 2024: 14; 2025: 5; 2026: 9.

87 papers.

Sort:

By area:

  1. 2022From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagationcited by 141
  2. 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
  3. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 129
  4. 2021What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methodscited by 98
  5. 2024The Hidden Attention of Mamba Modelscited by 88
  6. 2021Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysiscited by 65
  7. 2021On Guaranteed Optimal Robust Explanations for NLP Modelscited by 54
  8. 2021Evaluating Saliency Methods for Neural Language Modelscited by 37
  9. 2021Explainable AI: current status and future directionscited by 32
  10. 2021Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classificationcited by 29
  11. 2022Diffeomorphic Counterfactuals with Generative Modelscited by 29
  12. 2022Human Interpretation of Saliency-based Explanation Over Textcited by 25
38 more
  1. 2022Explainable Intrusion Detection Systems (X-IDS): A Survey of Current Methods, Challenges, and Opportunitiescited by 25
  2. 2022Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspacescited by 25
  3. 2021On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classificationcited by 21
  4. 2021Levels of explainable artificial intelligence for human-aligned conversational explanationscited by 21
  5. 2022Learning to Scaffold: Optimizing Model Explanations for Teachingcited by 20
  6. 2021Interpreting Deep Learning Models in Natural Language Processing: A Reviewcited by 19
  7. 2021Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Saliencecited by 16
  8. 2023Interpretation of Time-Series Deep Models: A Surveycited by 15
  9. 2021Model Explainability in Deep Learning Based Natural Language Processingcited by 14
  10. 2023Being Right for Whose Right Reasons?cited by 12
  11. 2021Thermostat: A Large Collection of NLP Model Explanations and Analysis Toolscited by 11
  12. 2022Explainable AI for Bioinformatics: Methods, Tools, and Applicationscited by 11
  13. 2023Don't be fooled: label leakage in explanation methods and the importance of their quantitative evaluationcited by 11
  14. 2021Flexible Instance-Specific Rationalization of NLP Modelscited by 10
  15. 2025A Close Look at Decomposition-based XAI-Methods for Transformer Language Modelscited by 10
  16. 2022How explainable are adversarially-robust CNNs?cited by 9
  17. 2024Explaining Text Similarity in Transformer Modelscited by 9
  18. 2024A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Futurecited by 9
  19. 2022Visualizing and Understanding Contrastive Learningcited by 7
  20. 2022Explaining Image Classifiers with Multiscale Directional Image Representationcited by 7
  21. 2024Layer-Wise Relevance Propagation with Conservation Property for ResNetcited by 7
  22. 2021Where do Models go Wrong? Parameter-Space Saliency Maps for Explainabilitycited by 6
  23. 2024SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generationcited by 6
  24. 2025Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainabilitycited by 6
  25. 2021Explainability: Relevance based Dynamic Deep Learning Algorithm for Fault Detection and Diagnosis in Chemical Processescited by 5
  26. 2021Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?cited by 5
  27. 2022Explainable Online Lane Change Predictions on a Digital Twin with a Layer Normalized LSTM and Layer-wise Relevance Propagationcited by 5
  28. 2022ReX: A Framework for Incorporating Temporal Information in Model-Agnostic Local Explanation Techniquescited by 5
  29. 2022Feature Importance for Time Series Data: Improving KernelSHAPcited by 5
  30. 2023Decoding Layer Saliency in Language Transformerscited by 5
  31. 2022Don't Get Me Wrong: How to Apply Deep Visual Interpretations to Time Seriescited by 4
  32. 2022Implicit N-grams Induced by Recurrencecited by 4
  33. 2022Explainable Artificial Intelligence: Precepts, Methods, and Opportunities for Research in Constructioncited by 4
  34. 2024SIDU-TXT: An XAI Algorithm for NLP with a Holistic Assessment Approachcited by 4
  35. 2021On the Post-hoc Explainability of Deep Echo State Networks for Time Series Forecasting, Image and Video Classificationcited by 3
  36. 2021Do End-to-End Speech Recognition Models Care About Context?cited by 3
  37. 2021Evaluating deep transfer learning for whole-brain cognitive decodingcited by 3
  38. 2022A Rigorous Study Of The Deep Taylor Decompositioncited by 3

50 most cited of 87 All 87 (JSON)