mlsanityData to 7 Oct 2026

SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers

arXiv 2103.12279 ↗First posted 23 Mar 2021cs.CLcited by 44

Not on the map. Why?

Abstract (arXiv)

We introduce SelfExplain, a novel self-explaining model that explains a text classifier's predictions using phrase-based concepts. SelfExplain augments existing neural classifiers by adding (1) a globally interpretable layer that identifies the most influential concepts in the training set for a given sample and (2) a locally interpretable layer that quantifies the contribution of each local input concept by computing a relevance score relative to the predicted label. Experiments across five text-classification datasets show that SelfExplain facilitates interpretability without sacrificing performance. Most importantly, explanations from SelfExplain show sufficiency for model predictions and are perceived as adequate, trustworthy and understandable by human judges compared to existing widely-used baselines.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). Builds on 55 of its 71 references that are in the map. First posted on arXiv 23 Mar 2021.

Builds on

55 of 71 references.

References · 55

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  7. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  8. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  9. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  10. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  11. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  12. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
38 more
  1. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  2. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  3. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  4. 2015Teaching Machines to Read and Comprehendcited by 1,039
  5. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
  6. 2020Concept Bottleneck Modelscited by 1,022
  7. 2019Attention is not Explanationcited by 916
  8. 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 864
  9. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  10. 2016The Mythos of Model Interpretabilitycited by 716
  11. 2018Annotation Artifacts in Natural Language Inference Datacited by 656
  12. 2019Attention is not not Explanationcited by 629
  13. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
  14. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 523
  15. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  16. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  17. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  18. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
  19. 2019Is Attention Interpretable?cited by 387
  20. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  21. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 346
  22. 2019Mitigating Gender Bias in Natural Language Processing: Literature Reviewcited by 287
  23. 2016Rationalizing Neural Predictionscited by 281
  24. 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
  25. 2015Visualizing and Understanding Neural Models in NLPcited by 199
  26. 2018Constituency Parsing with a Self-Attentive Encodercited by 196
  27. 2020Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?cited by 189
  28. 2020Measuring Association Between Labels and Free-Text Rationalescited by 159
  29. 2020Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functionscited by 144
  30. 2019Interpretable Neural Predictions with Differentiable Binary Variablescited by 126
  31. 2020Learning to Faithfully Rationalize by Constructioncited by 113
  32. 2019Learning to Deceive with Attention-Based Explanationscited by 111
  33. 2014Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS)cited by 109
  34. 2019Rethinking Cooperative Rationalization: Introspective Extraction and Complement Controlcited by 96
  35. 2019Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptionscited by 81
  36. 2015The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classificationcited by 76
  37. 2018Hierarchical interpretations for neural network predictionscited by 66
  38. 2020Differentiable Reasoning over a Virtual Knowledge Basecited by 39

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 9; 2023: 12; 2024: 8; 2025: 9; 2026: 1.

44 papers.

Sort:

By area:

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 129
  3. 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 97
  4. 2021Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updatescited by 27
  5. 2024On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMscited by 24
  6. 2021Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexicacited by 23
  7. 2022ProtoTEx: Explaining Model Decisions with Prototype Tensorscited by 21
  8. 2023D-Separation for Causal Self-Explanationcited by 21
  9. 2023Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneckcited by 21
  10. 2021Interpreting Deep Learning Models in Natural Language Processing: A Reviewcited by 19
  11. 2023Towards Trustworthy Explanation: On Causal Rationalizationcited by 19
  12. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
32 more
  1. 2022Investigating the Benefits of Free-Form Rationalescited by 13
  2. 2023Are Human Explanations Always Helpful? Towards Objective Evaluation of Human Natural Language Explanationscited by 13
  3. 2024Latent Concept-based Explanation of NLP Modelscited by 13
  4. 2023MGR: Multi-generator Based Rationalizationcited by 12
  5. 2025Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasonscited by 11
  6. 2023Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecturecited by 10
  7. 2024Towards Modeling Uncertainties of Self-explaining Neural Networks via Conformal Predictioncited by 10
  8. 2021Efficient Explanations from Empirical Explainerscited by 9
  9. 2022Are Shortest Rationales the Best Explanations for Human Understanding?cited by 8
  10. 2022Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switchingcited by 6
  11. 2025Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanationscited by 6
  12. 2025Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilizationcited by 6
  13. 2025Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasetscited by 6
  14. 2022Learning to Select Prototypical Parts for Interpretable Sequential Data Modelingcited by 4
  15. 2025Model-Agnostic Policy Explanations with Large Language Modelscited by 4
  16. 2022StyLEx: Explaining Style Using Human Lexical Annotationscited by 3
  17. 2024Extracting Lexical Features from Dialects via Interpretable Dialect Classifierscited by 3
  18. 2024Linearly-Interpretable Concept Embedding Models for Text Analysiscited by 3
  19. 2026IMRNNs: An Efficient Method for Interpretable Dense Retrieval via Embedding Modulationcited by 3
  20. 2023PROMINET: Prototype-based Multi-View Network for Interpretable Email Response Predictioncited by 2
  21. 2024Advancing Interpretability in Text Classification through Prototype Learningcited by 2
  22. 2021Beyond Tracking: Using Deep Learning to Discover Novel Interactions in Biological Swarmscited by 1
  23. 2022Unsupervised Keyphrase Extraction via Interpretable Neural Networkscited by 1
  24. 2023How to choose "Good" Samples for Text Data Augmentationcited by 1
  25. 2023Wrapper Boxes: Faithful Attribution of Model Predictions to Training Datacited by 1
  26. 2024PEACH: Pretrained-embedding Explanation Across Contextual and Hierarchical Structurecited by 1
  27. 2025Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discoverycited by 1
  28. 2025Cross-Layer Discrete Concept Discovery for Interpreting Language Modelscited by 1
  29. 2023Multidimensional Perceptron for Efficient and Explainable Long Text Classificationcited by 0
  30. 2023Explainable Authorship Identification in Cultural Heritage Applications: Analysis of a New Perspectivecited by 0
  31. 2024Discovering influential text using convolutional neural networkscited by 0
  32. 2025Enhancing Job Salary Prediction with Disentangled Composition Effect Modeling: A Neural Prototyping Approachcited by 0