mlsanityData to 7 Oct 2026

Interpreting Recurrent and Attention-Based Neural Models: a Case Study on Natural Language Inference

arXiv 1808.03894 ↗First posted 12 Aug 2018cs.CL cs.AI cs.LGcited by 26

Not on the map. Why?

Abstract (arXiv)

Deep learning models have achieved remarkable success in natural language inference (NLI) tasks. While these models are widely explored, they are hard to interpret and it is often unclear how and why they actually work. In this paper, we take a step toward explaining such deep learning based models through a case study on a popular neural model for NLI. In particular, we propose to interpret the intermediate layers of NLI models by visualizing the saliency of attention and LSTM gating signals. We present several examples for which our methods are able to reveal interesting insights and identify the critical information contributing to the model decisions.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 9; 2023: 1; 2024: 3; 2025: 4.

26 papers.

Sort:

  1. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  2. 2022Visual correspondence-based explanations improve AI robustness and human-AI team accuracycited by 37
  3. 2021Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classificationcited by 29
  4. 2022Deconfounding Legal Judgment Prediction for European Court of Human Rights Cases Towards Better Alignment with Expertscited by 24
  5. 2021Interpreting Deep Learning Models in Natural Language Processing: A Reviewcited by 19
  6. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  7. 2022Fooling Explanations in Text Classifierscited by 13
  8. 2021Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Maskscited by 12
  9. 2022More Interpretable Graph Similarity Computation via Maximum Common Subgraph Inferencecited by 8
  10. 2021SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoningcited by 7
  11. 2021Enhanced Aspect-Based Sentiment Analysis Models with Progressive Self-supervised Attention Learningcited by 5
  12. 2024Faithful and Accurate Self-Attention Attribution for Message Passing Neural Networks via the Computation Tree Viewpointcited by 5
14 more
  1. 2022Controlling the Focus of Pretrained Language Generation Modelscited by 4
  2. 2025Fake News Detection After LLM Laundering: Measurement and Explanationcited by 4
  3. 2021LioNets: A Neural-Specific Local Interpretation Technique Exploiting Penultimate Layer Informationcited by 3
  4. 2021Do Models Learn the Directionality of Relations? A New Evaluation: Relation Direction Recognitioncited by 2
  5. 2021Reason induced visual attention for explainable autonomous drivingcited by 2
  6. 2022Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classificationcited by 2
  7. 2023Towards Reconciling Usability and Usefulness of Explainable AI Methodologiescited by 2
  8. 2022POTATO: exPlainable infOrmation exTrAcTion framewOrkcited by 1
  9. 2024On Explaining with Attention Matricescited by 1
  10. 2025A Study of the Plausibility of Attention between RNN Encoders in Natural Language Inferencecited by 1
  11. 2022Toward a traceable, explainable, and fairJD/Resume recommendation systemcited by 0
  12. 2022STRATA: Word Boundaries & Phoneme Recognition From Continuous Urdu Speech using Transfer Learning, Attention, & Data Augmentationcited by 0
  13. 2024Using Interpretation Methods for Model Enhancementcited by 0
  14. 2025Hierarchical Attention Network for Interpretable ECG-based Heart Disease Classificationcited by 0