mlsanityData to 14 Oct 2026

Understanding Hidden Memories of Recurrent Neural Networks

arXiv 1710.10777 ↗First posted 30 Oct 2017cs.CL cs.AIcited by 44

Not on the map. Why?

Abstract (arXiv)

Recurrent neural networks (RNNs) have been successfully applied to various natural language processing (NLP) tasks and achieved better results than conventional methods. However, the lack of understanding of the mechanisms behind their effectiveness limits further improvements on their architectures. In this paper, we present a visual analytics method for understanding and comparing RNN models for NLP tasks. We propose a technique to explain the function of individual hidden state units based on their expected response to input texts. We then co-cluster hidden state units and words based on the expected response and visualize co-clustering results as memory chips and word clouds to provide more structured knowledge on RNNs' hidden states. We also propose a glyph-based sequence visualization based on aggregate information to analyze the behavior of an RNN's hidden state at the sentence-level. The usability and effectiveness of our method are demonstrated through case studies and reviews from domain experts.

Key facts. Cited by 44 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 12; 2023: 10; 2024: 9; 2025: 3; 2026: 4.

44 papers.

Sort:

By area:

  1. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 130
  2. 2022Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Modelscited by 70
  3. 2021Is Sparse Attention more Interpretable?cited by 31
  4. 2022The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizationscited by 29
  5. 2022Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignmentcited by 27
  6. 2023Visual Analytics For Machine Learning: A Data Perspective Surveycited by 25
  7. 2022A Unified Understanding of Deep NLP Models for Text Classificationcited by 18
  8. 2021A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networkscited by 14
  9. 2022Diagnosing Ensemble Few-Shot Classifierscited by 13
  10. 2021GenNI: Human-AI Collaboration for Data-Backed Text Generationcited by 11
  11. 2021Towards Visual Explainable Active Learning for Zero-Shot Classificationcited by 10
  12. 2022Learning-From-Disagreement: A Model Comparison and Visual Analytics Frameworkcited by 10
32 more
  1. 2024Understanding Large Language Model Behaviors through Interactive Counterfactual Generation and Analysiscited by 8
  2. 2024JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Modelscited by 7
  3. 2021Explainable Adversarial Attacks in Deep Neural Networks Using Activation Profilescited by 6
  4. 2022A Visual Analytics System for Improving Attention-based Traffic Forecasting Modelscited by 6
  5. 2022ShortcutLens: A Visual Analytics Approach for Exploring Shortcuts in Natural Language Understanding Datasetcited by 6
  6. 2023DeepSeer: Interactive RNN Explanation and Debugging via State Abstractioncited by 6
  7. 2022Visualizing and Explaining Language Modelscited by 4
  8. 2023LUNA: A Model-Based Universal Analysis Framework for Large Language Modelscited by 4
  9. 2021Understanding Spending Behavior: Recurrent Neural Network Explanation and Interpretationcited by 3
  10. 2022Visual Analysis of Neural Architecture Spaces for Summarizing Design Principlescited by 3
  11. 2023Designing a Direct Feedback Loop between Humans and Convolutional Neural Networks through Local Explanationscited by 3
  12. 2023A Distance Correlation-Based Approach to Characterize the Effectiveness of Recurrent Neural Networks for Time Series Forecastingcited by 3
  13. 2023Are We Closing the Loop Yet? Gaps in the Generalizability of VIS4ML Researchcited by 3
  14. 2023A Review of Hybrid and Ensemble in Deep Learning for Natural Language Processingcited by 3
  15. 2024EL-VIT: Probing Vision Transformer with Interactive Visualizationcited by 3
  16. 2023CommonsenseVIS: Visualizing and Understanding Commonsense Reasoning Capabilities of Natural Language Modelscited by 2
  17. 2024Abstracted Trajectory Visualization for Explainability in Reinforcement Learningcited by 2
  18. 2024JailbreakHunter: A Visual Analytics Approach for Jailbreak Prompts Discovery from Large-Scale Human-LLM Conversational Datasetscited by 2
  19. 2023Towards Better Modeling with Missing Data: A Contrastive Learning-based Visual Analytics Perspectivecited by 1
  20. 2023Advancing Perception in Artificial Intelligence through Principles of Cognitive Sciencecited by 1
  21. 2024TrafPS: A Shapley-based Visual Analytics Approach to Interpret Trafficcited by 1
  22. 2024Multiway Multislice PHATE: Visualizing Hidden Dynamics of RNNs through Trainingcited by 1
  23. 2024POEM: Interactive Prompt Optimization for Enhancing Multimodal Reasoning of Large Language Modelscited by 1
  24. 2024RuleExplorer: A Scalable Matrix Visualization for Understanding Tree Ensemble Classifierscited by 1
  25. 2025Understanding Mental Health Content on Social Media and Its Effect Towards Suicidal Ideationcited by 1
  26. 2025NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Modelscited by 1
  27. 2026KEditVis: A Visual Analytics System for Knowledge Editing of Large Language Modelscited by 1
  28. 2026Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learningcited by 1
  29. 2022Towards Efficient Visual Simplification of Computational Graphs in Deep Neural Networkscited by 0
  30. 2025Repetitive Contrastive Learning Enhances Mamba's Selectivity in Time Series Predictioncited by 0
  31. 2026Parallel Recursive LSTMcited by 0
  32. 2026Learning to Remember: Distilling Memory Retention for Compact Recurrent Neural Networkscited by 0