mlsanityData to 14 Oct 2026

ProtoTEx: Explaining Model Decisions with Prototype Tensors

arXiv 2204.05426 ↗First posted 11 Apr 2022cs.CL cs.AI cs.CYcited by 21

Not on the map. Why?

Abstract (arXiv)

We present ProtoTEx, a novel white-box NLP classification architecture based on prototype networks. ProtoTEx faithfully explains model decisions based on prototype tensors that encode latent clusters of training examples. At inference time, classification decisions are based on the distances between the input text and the prototype tensors, explained via the training examples most similar to the most influential prototypes. We also describe a novel interleaved training algorithm that effectively handles classes characterized by the absence of indicative features. On a propaganda detection task, ProtoTEx accuracy matches BART-large and exceeds BERT-large with the added benefit of providing faithful explanations. A user study also shows that prototype-based explanations help non-experts to better recognize propaganda in online news.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 37 of its 55 references that are in the map. First posted on arXiv 11 Apr 2022.

Builds on

37 of 55 references.

References · 37

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  5. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
  6. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
  7. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  8. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 1,006
  9. 2019Attention is not Explanationcited by 929
  10. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  11. 2019Attention is not not Explanationcited by 636
  12. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 599
25 more
  1. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 399
  2. 2019Is Attention Interpretable?cited by 389
  3. 2016Rationalizing Neural Predictionscited by 281
  4. 2020Questioning the AI: Informing Design Practices for Explainable AI User Experiencescited by 253
  5. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  6. 2020Explainable Automated Fact-Checking for Public Health Claimscited by 211
  7. 2020A Survey of the State of Explainable AI for Natural Language Processingcited by 206
  8. 2020Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?cited by 190
  9. 2021Automated Fact-Checking for Assisting Human Fact-Checkerscited by 144
  10. 2019Fine-Grained Analysis of Propaganda in News Articlescited by 133
  11. 2020Generating Fact Checking Explanationscited by 132
  12. 2019Interpretable Neural Predictions with Differentiable Binary Variablescited by 126
  13. 2020Learning to Faithfully Rationalize by Constructioncited by 113
  14. 2019Learning to Deceive with Attention-Based Explanationscited by 111
  15. 2018DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learningcited by 100
  16. 2017Generating Sentences by Editing Prototypescited by 88
  17. 2020Explainable Automated Fact-Checking: A Surveycited by 83
  18. 2015The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classificationcited by 76
  19. 2020A Survey on Computational Propaganda Detectioncited by 70
  20. 2019Interpretable Image Recognition with Hierarchical Prototypescited by 65
  21. 2021SelfExplain: A Self-Explaining Architecture for Neural Text Classifierscited by 44
  22. 2017Human-in-the-loop Artificial Intelligencecited by 40
  23. 2021Putting Humans in the Natural Language Processing Loop: A Surveycited by 40
  24. 2020Why do you think that? Exploring Faithful Sentence-Level Rationales Without Supervisioncited by 15
  25. 2018Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Predictioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 6; 2024: 5; 2025: 6; 2026: 1.

21 papers.

Sort:

By area:

  1. 2023Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrongcited by 51
  2. 2025Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checkingcited by 29
  3. 2024On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMscited by 25
  4. 2023Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneckcited by 22
  5. 2022Robust and Explainable Identification of Logical Fallacies in Natural Language Argumentscited by 12
  6. 2023InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanationscited by 11
  7. 2023Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Modelscited by 7
  8. 2022This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical Textcited by 6
  9. 2025Distilling Knowledge from Large Language Models: A Concept Bottleneck Model for Hate and Counter Speech Recognitioncited by 5
  10. 2024GAProtoNet: A Multi-head Graph Attention-based Prototypical Network for Interpretable Text Classificationcited by 4
  11. 2023Robust Text Classification: Analyzing Prototype-Based Networkscited by 3
  12. 2025GraPPI: A Retrieve-Divide-Solve GraphRAG Framework for Large-scale Protein-protein Interaction Explorationcited by 3
9 more
  1. 2024Regulation of Language Models With Interpretability Will Likely Result In A Performance Trade-Offcited by 2
  2. 2022Intermediate Entity-based Sparse Interpretable Representation Learningcited by 1
  3. 2023Wrapper Boxes: Faithful Attribution of Model Predictions to Training Datacited by 1
  4. 2024Exploring the Plausibility of Hate and Counter Speech Detectors with Explainable AIcited by 1
  5. 2024They Look Like Each Other: Case-based Reasoning for Explainable Depression Detection on Twitter using Large Language Modelscited by 1
  6. 2025A Transformer and Prototype-based Interpretable Model for Contextual Sarcasm Detectioncited by 1
  7. 2025Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discoverycited by 1
  8. 2026Coupling Local Context and Global Semantic Prototypes via a Hierarchical Architecture for Rhetorical Roles Labelingcited by 1
  9. 2025ProtoSiTex: Learning Semi-Interpretable Prototypes for Multi-label Text Classificationcited by 0