mlsanityData to 7 Oct 2026

Rationalization through Concepts

arXiv 2105.04837 ↗First posted 11 May 2021cs.CL cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

Automated predictions require explanations to be interpretable by humans. One type of explanation is a rationale, i.e., a selection of input features such as relevant text snippets from which the model computes the outcome. However, a single overall selection does not provide a complete explanation, e.g., weighing several aspects for decisions. To this end, we present a novel self-interpretable model called ConRAT. Inspired by how human explanations for high-level decisions are often based on key concepts, ConRAT extracts a set of text snippets as concepts and infers which ones are described in the document. Then, it explains the outcome with a linear aggregation of concepts. Two regularizers drive ConRAT to build interpretable concepts. In addition, we propose two techniques to boost the rationale and predictive performance further. Experiments on both single- and multi-aspect sentiment classification tasks show that ConRAT is the first to generate concepts that align with human rationalization while using only the overall label. Further, it outperforms state-of-the-art methods trained on each aspect label independently.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 36 of its 51 references that are in the map. First posted on arXiv 11 May 2021.

Builds on

36 of 51 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  5. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  6. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  7. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  8. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  9. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  10. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  11. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  12. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
24 more
  1. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  2. 2020Concept Bottleneck Modelscited by 1,022
  3. 2019Attention is not Explanationcited by 916
  4. 2019Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Prunedcited by 844
  5. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  6. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 515
  7. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  8. 2019Revealing the Dark Secrets of BERTcited by 300
  9. 2016Rationalizing Neural Predictionscited by 281
  10. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  11. 2019Explaining Classifiers with Causal Concept Effect (CaCE)cited by 135
  12. 2020Invariant Rationalizationcited by 131
  13. 2019Interpretable Neural Predictions with Differentiable Binary Variablescited by 126
  14. 2020Learning to Faithfully Rationalize by Constructioncited by 113
  15. 2019Learning to Deceive with Attention-Based Explanationscited by 111
  16. 2019Rethinking Cooperative Rationalization: Introspective Extraction and Complement Controlcited by 96
  17. 2020An Information Bottleneck Approach for Controlling Conciseness in Rationale Extractioncited by 69
  18. 2017A causal framework for explaining the predictions of black-box sequence-to-sequence modelscited by 58
  19. 2018Deriving Machine Attention from Human Rationalescited by 54
  20. 2019A Game Theoretic Approach to Class-wise Selective Rationalizationcited by 32
  21. 2016TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependencycited by 27
  22. 2019EDUCE: Explaining model Decisions through Unsupervised Concepts Extractioncited by 13
  23. 2020Interacting with Explanations through Critiquingcited by 9
  24. 2019Learning Decision Trees Recurrently Through Communicationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 3; 2023: 6; 2024: 3; 2025: 3; 2026: 1.

19 papers.

Sort:

  1. 2022Interactive Concept Bottleneck Modelscited by 79
  2. 2024Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Eracited by 45
  3. 2021Understanding Interlocking Dynamics of Cooperative Rationalizationcited by 36
  4. 2021What to Learn, and How: Toward Effective Learning from Rationalescited by 25
  5. 2024Interpretable Concept Bottlenecks to Align Reinforcement Learning Agentscited by 23
  6. 2023Rationalization for Explainable NLP: A Surveycited by 22
  7. 2023D-Separation for Causal Self-Explanationcited by 21
  8. 2021Interpreting Deep Learning Models in Natural Language Processing: A Reviewcited by 19
  9. 2023Towards Trustworthy Explanation: On Causal Rationalizationcited by 19
  10. 2023COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP taskscited by 16
  11. 2025Explainability in Practice: A Survey of Explainable NLP Across Various Domainscited by 11
  12. 2024Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discoverycited by 8
7 more
  1. 2023Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answeringcited by 6
  2. 2023A Survey of Explainable AI in Deep Visual Modeling: Methods and Metricscited by 4
  3. 2022Assistive Recipe Editing through Critiquingcited by 2
  4. 2022Interlock-Free Multi-Aspect Rationalization for Text Classificationcited by 1
  5. 2025Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discoverycited by 1
  6. 2025Text Rationalization for Robust Causal Effect Estimationcited by 1
  7. 2026Matryoshka Concept Bottleneck Modelscited by 0