mlsanityData to 7 Oct 2026

Axiomatic Attribution for Deep Networks

arXiv 1703.01365 ↗First posted 4 Mar 2017cs.LGcited by 3,350

Not on the map. Why?

Cited by 54 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We study the problem of attributing the prediction of a deep network to its input features, a problem previously studied by several other works. We identify two fundamental axioms---Sensitivity and Implementation Invariance that attribution methods ought to satisfy. We show that they are not satisfied by most known attribution methods, which we consider to be a fundamental weakness of those methods. We use the axioms to guide the design of a new attribution method called Integrated Gradients. Our method requires no modification to the original network and is extremely simple to implement; it just needs a few calls to the standard gradient operator. We apply this method to a couple of image models, a couple of text models and a chemistry model, demonstrating its ability to debug networks, to extract rules from a network, and to enable users to engage with models better.

Key facts. Cited by 3,350 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 434; 2022: 509; 2023: 577; 2024: 618; 2025: 614; 2026: 597.

3,350 papers.

Sort:

By area:

  1. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  2. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  3. 2023Towards Automated Circuit Discovery for Mechanistic Interpretabilitycited by 700
  4. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 690
  5. 2021Knowledge Neurons in Pretrained Transformerscited by 590
  6. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  7. 2021Dynabench: Rethinking Benchmarking in NLPcited by 447
  8. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  9. 2024Mechanistic Interpretability for AI Safety -- A Reviewcited by 415
  10. 2024Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Modelscited by 412
  11. 2021Causal Abstractions of Neural Networkscited by 401
  12. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generationcited by 376
38 more
  1. 2023Explainability for Large Language Models: A Surveycited by 331
  2. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 316
  3. 2024Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modificationscited by 220
  4. 2021Trustworthy AI: From Principles to Practicescited by 206
  5. 2025AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoderscited by 199
  6. 2023Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretabilitycited by 194
  7. 2023Interpreting CLIP's Image Representation via Text-Based Decompositioncited by 189
  8. 2022CRAFT: Concept Recursive Activation FacTorization for Explainabilitycited by 177
  9. 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
  10. 2024Improving Dictionary Learning with Gated Sparse Autoencoderscited by 171
  11. 2022The Unreliability of Explanations in Few-shot Prompting for Textual Reasoningcited by 169
  12. 2022Protein Representation Learning by Geometric Structure Pretrainingcited by 161
  13. 2022The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspectivecited by 156
  14. 2021Post-hoc Interpretability for Neural NLP: A Surveycited by 155
  15. 2024A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoderscited by 148
  16. 2024Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanismscited by 144
  17. 2022From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagationcited by 141
  18. 2021From Show to Tell: A Survey on Deep Learning-based Image Captioningcited by 137
  19. 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
  20. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 129
  21. 2021IA-RED2: Interpretability-Aware Redundancy Reduction for Vision Transformerscited by 127
  22. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 126
  23. 2022OpenXAI: Towards a Transparent Evaluation of Model Explanationscited by 125
  24. 2021FastSHAP: Real-Time Shapley Value Estimationcited by 123
  25. 2021Acquisition of Chess Knowledge in AlphaZerocited by 120
  26. 2021Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypescited by 120
  27. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  28. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  29. 2024AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformerscited by 116
  30. 2024Towards Interpreting Visual Information Processing in Vision-Language Modelscited by 115
  31. 2021Do Concept Bottleneck Models Learn as Intended?cited by 114
  32. 2021Salient ImageNet: How to discover spurious features in Deep Learning?cited by 114
  33. 2022Algorithms to estimate Shapley value feature attributionscited by 114
  34. 2024A Practical Review of Mechanistic Interpretability for Transformer-Based Language Modelscited by 113
  35. 2024Rethinking Interpretability in the Era of Large Language Modelscited by 110
  36. 2023A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimationcited by 108
  37. 2021Inducing Causal Structure for Interpretable Neural Networkscited by 107
  38. 2023Artificial Intelligence for Digital and Computational Pathologycited by 106

50 most cited of 3,350 All 3,350 (JSON)