mlsanityData to 7 Oct 2026

Fixed Point Explainability

arXiv 2505.12421 ↗First posted 18 May 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper introduces a formal notion of fixed point explanations, inspired by the "why regress" principle, to assess, through recursive applications, the stability of the interplay between a model and its explainer. Fixed point explanations satisfy properties like minimality, stability, and faithfulness, revealing hidden model behaviours and explanatory weaknesses. We define convergence conditions for several classes of explainers, from feature-based to mechanistic tools like Sparse AutoEncoders, and we report quantitative and qualitative results for several datasets and models, including LLMs such as Llama-3.3-70B.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 54 of its 83 references that are in the map. First posted on arXiv 18 May 2025.

Builds on

54 of 83 references.

References · 54

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  7. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  8. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  9. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  10. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,359
  11. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  12. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
38 more
  1. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  2. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
  3. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  4. 2017Interpretation of Neural Networks is Fragilecited by 443
  5. 2023Explainability for Large Language Models: A Surveycited by 331
  6. 2019Counterfactual Visual Explanationscited by 312
  7. 2018On the Robustness of Interpretability Methodscited by 310
  8. 2019Interpretable machine learning: definitions, methods, and applicationscited by 303
  9. 2019Causality for Machine Learningcited by 242
  10. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  11. 2020A Survey on the Explainability of Supervised Machine Learningcited by 225
  12. 2019Explanations can be manipulated and geometry is to blamecited by 215
  13. 2016Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Modelscited by 212
  14. 2017Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Modelscited by 202
  15. 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
  16. 2022CRAFT: Concept Recursive Activation FacTorization for Explainabilitycited by 177
  17. 2020Reliable Post hoc Explanations: Modeling Uncertainty in Explainabilitycited by 125
  18. 2020Principles and Practice of Explainable Machine Learningcited by 99
  19. 2018Interpretable Deep Learning under Firecited by 74
  20. 2019Interpretable Image Recognition with Hierarchical Prototypescited by 64
  21. 2021On Explaining Random Forests with SATcited by 57
  22. 2020Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delaycited by 56
  23. 2021On Guaranteed Optimal Robust Explanations for NLP Modelscited by 54
  24. 2020On Explaining Decision Treescited by 49
  25. 2019Robust Attribution Regularizationcited by 46
  26. 2021A Review on Explainability in Multimodal Deep Neural Netscited by 46
  27. 2021Local Explanations via Necessity and Sufficiency: Unifying Theory and Practicecited by 45
  28. 2020Towards Robust Explanations for Deep Neural Networkscited by 43
  29. 2020Smoothed Geometry for Robust Attributioncited by 38
  30. 2019Can I Trust the Explainer? Verifying Post-hoc Explanatory Methodscited by 37
  31. 2021How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Reviewcited by 36
  32. 2022ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Modelcited by 34
  33. 2022Causal Explanations and XAIcited by 30
  34. 2022VeriX: Towards Verified Explainability of Deep Neural Networkscited by 30
  35. 2022Formalising the Robustness of Counterfactual Explanations for Neural Networkscited by 24
  36. 2022Robust Explanation Constraints for Neural Networkscited by 23
  37. 2021Certifiably Robust Interpretation via Renyi Differential Privacycited by 10
  38. 2021When and How to Fool Explainable Models (and Humans) with Adversarial Examplescited by 10

50 most cited of 54 All 54 (JSON)

Built on by

Not cited yet.