mlsanityData to 14 Oct 2026

Do Not Trust Additive Explanations

arXiv 1903.11420 ↗First posted 27 Mar 2019cs.LG stat.MLcited by 16

Not on the map. Why?

Abstract (arXiv)

Explainable Artificial Intelligence (XAI)has received a great deal of attention recently. Explainability is being presented as a remedy for the distrust of complex and opaque models. Model agnostic methods such as LIME, SHAP, or Break Down promise instance-level interpretability for any complex machine learning model. But how faithful are these additive explanations? Can we rely on additive explanations for non-additive models? In this paper, we (1) examine the behavior of the most popular instance-level explanations under the presence of interactions, (2) introduce a new method that detects interactions for instance-level explanations, (3) perform a large scale benchmark to see how frequently additive explanations may be misleading.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 1; 2023: 0; 2024: 5; 2025: 3; 2026: 3.

16 papers.

Sort:

  1. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 367
  2. 2021PredDiff: Explanations and Interactions from Conditional Expectationscited by 17
  3. 2021Show or Suppress? Managing Input Uncertainty in Machine Learning Model Explanationscited by 15
  4. 2024Why do explanations fail? A typology and discussion on failures in XAIcited by 6
  5. 2024X Hacking: The Threat of Misguided AutoMLcited by 5
  6. 2024When Can You Trust Your Explanations? A Robustness Analysis on Feature Importancescited by 5
  7. 2025shapr: Explaining Machine Learning Models with Conditional Shapley Values in R and Pythoncited by 5
  8. 2025Trustworthy AI Must Account for Interactionscited by 5
  9. 2021Consistent Sufficient Explanations and Minimal Local Rules for explaining regression and classification modelscited by 4
  10. 2025ProtoMedX: Towards Explainable Multi-Modal Prototype Learning for Bone Health Classificationcited by 2
  11. 2024Neuro-Symbolic Rule Listscited by 1
  12. 2026Interpretable and Explainable Surrogate Modeling for Simulations: A State-of-the-Art Survey and Perspectives on Explainable AI for Decision-Makingcited by 1
4 more
  1. 2022Causality-Aware Local Interpretable Model-Agnostic Explanationscited by 0
  2. 2024Succinct Interaction-Aware Explanationscited by 0
  3. 2026Reliable XAI Explanations in Sudden Cardiac Death Prediction for Chagas Cardiomyopathycited by 0
  4. 2026Beyond Explaining Predictions: Logic-Based Explanations for Confidence in Machine Learning Modelscited by 0