mlsanityData to 14 Oct 2026

Self-explaining deep models with logic rule reasoning

arXiv 2210.07024 ↗First posted 13 Oct 2022cs.AI cs.LG cs.LOcited by 13

Not on the map. Why?

Abstract (arXiv)

We present SELOR, a framework for integrating self-explaining capabilities into a given deep model to achieve both high prediction performance and human precision. By "human precision", we refer to the degree to which humans agree with the reasons models provide for their predictions. Human precision affects user trust and allows users to collaborate closely with the model. We demonstrate that logic rule explanations naturally satisfy human precision with the expressive power required for good predictive performance. We then illustrate how to enable a deep model to predict and explain with logic rules. Our method does not require predefined logic rule sets or human annotations and can be learned efficiently and easily with widely-used deep learning modules in a differentiable way. Extensive experiments show that our method gives explanations closer to human decision logic than other methods while maintaining the performance of deep learning models.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 33 of its 69 references that are in the map. First posted on arXiv 13 Oct 2022.

Builds on

33 of 69 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  6. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  7. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  8. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  9. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  10. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  11. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  12. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
21 more
  1. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  2. 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 372
  3. 2016Rationalizing Neural Predictionscited by 281
  4. 2017Learning Explanatory Rules from Noisy Datacited by 211
  5. 2020Making deep neural networks right for the right scientific reasons by interacting with their explanationscited by 142
  6. 2015Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction modelcited by 140
  7. 2020Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanationscited by 94
  8. 2017Learning to Infer Graphics Programs from Hand-Drawn Imagescited by 74
  9. 2020Human Factors in Model Interpretability: Industry Practices, Challenges, and Needscited by 74
  10. 2019Interpretable and Steerable Sequence Learning via Prototypescited by 72
  11. 2018Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMscited by 67
  12. 2016Scalable Bayesian Rule Listscited by 64
  13. 2020From Statistical Relational to Neuro-Symbolic Artificial Intelligencecited by 63
  14. 2016Automatic Text Scoring Using Neural Networkscited by 51
  15. 2017Learning Certifiably Optimal Rule Lists for Categorical Datacited by 50
  16. 2020FIND: Human-in-the-Loop Debugging Deep Text Classifierscited by 40
  17. 2018Neural-Guided Deductive Search for Real-Time Program Synthesis from Examplescited by 39
  18. 2018HOUDINI: Lifelong Learning as Program Synthesiscited by 38
  19. 2020Analysis of Q-learning with Adaptation and Momentum Restart for Gradient Descentcited by 26
  20. 2016Nothing Else Matters: Model-Agnostic Explanations By Identifying Prediction Invariancecited by 9
  21. 2020Adversarial Infidelity Learning for Model Interpretationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 3; 2025: 3; 2026: 1.

13 papers.

Sort:

By area:

  1. 2023When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunitiescited by 90
  2. 2024Uncovering Safety Risks of Large Language Models through Concept Activation Vectorcited by 67
  3. 2022Going Beyond XAI: A Systematic Survey for Explanation-Guided Learningcited by 36
  4. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  5. 2023Learning by Self-Explainingcited by 17
  6. 2025Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasonscited by 12
  7. 2023Towards Interpretable Federated Learningcited by 11
  8. 2022Prototypical Fine-tuning: Towards Robust Performance Under Varying Data Sizescited by 10
  9. 2024Evaluating Readability and Faithfulness of Concept-based Explanationscited by 10
  10. 2024Logic Rules as Explanations for Legal Case Retrievalcited by 5
  11. 2025LogicCBMs: Logic-Enhanced Concept-Based Learningcited by 5
  12. 2023LR-XFL: Logical Reasoning-based Explainable Federated Learningcited by 4
1 more
  1. 2026Enhancing Safety of Large Language Models via Embedding Space Separationcited by 2