mlsanityData to 7 Oct 2026

How Interpretable and Trustworthy are GAMs?

arXiv 2006.06466 ↗First posted 11 Jun 2020cs.LG stat.MLcited by 44

Not on the map. Why?

Abstract (arXiv)

Generalized additive models (GAMs) have become a leading modelclass for interpretable machine learning. However, there are many algorithms for training GAMs, and these can learn different or even contradictory models, while being equally accurate. Which GAM should we trust? In this paper, we quantitatively and qualitatively investigate a variety of GAM algorithms on real and simulated datasets. We find that GAMs with high feature sparsity (only using afew variables to make predictions) can miss patterns in the data and be unfair to rare subpopulations. Our results suggest that inductive bias plays a crucial role in what interpretable models learn and that tree-based GAMs represent the best balance of sparsity, fidelity and accuracy and thus appear to be the most trustworthy GAM.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 14; 2023: 7; 2024: 5; 2025: 5; 2026: 3.

44 papers.

Sort:

By area:

  1. 2021A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Conceptscited by 90
  2. 2021NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learningcited by 88
  3. 2022TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversationscited by 65
  4. 2022The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanationscited by 41
  5. 2022Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifoldcited by 29
  6. 2022Sparse Interaction Additive Networks via Feature Interaction Detection and Sparse Selectioncited by 28
  7. 2022Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Valuescited by 25
  8. 2021Accuracy, Interpretability, and Differential Privacy via Explainable Boostingcited by 24
  9. 2023SaDI: A Self-adaptive Decomposed Interpretable Framework for Electric Load Forecasting under Extreme Eventscited by 21
  10. 2021GAM Changer: Editing Generalized Additive Models with Interactive Visualizationcited by 18
  11. 2021SurvNAM: The machine learning survival model explanationcited by 16
  12. 2022Data-Efficient and Interpretable Tabular Anomaly Detectioncited by 15
32 more
  1. 2022Differentially Private Estimation of Heterogeneous Causal Effectscited by 14
  2. 2022TimberTrek: Exploring and Curating Sparse Decision Trees with Interactive Visualizationcited by 13
  3. 2023Curve Your Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Modelscited by 12
  4. 2023GAM Coach: Towards Interactive and User-centered Algorithmic Recoursecited by 9
  5. 2021Ensembles of Random SHAPscited by 8
  6. 2022Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactionscited by 7
  7. 2022Interpretability with full complexity by constraining feature informationcited by 7
  8. 2021An Imprecise SHAP as a Tool for Explaining the Class Probability Distributions under Limited Training Datacited by 6
  9. 2022GAM(e) changer or not? An evaluation of interpretable machine learning models based on additive model constraintscited by 6
  10. 2021Attention-like feature explanation for tabular datacited by 3
  11. 2023SurvBeX: An explanation method of the machine learning survival models based on the Beran estimatorcited by 3
  12. 2023An Interpretable Machine Learning Model with Deep Learning-based Imaging Biomarkers for Diagnosis of Alzheimer's Diseasecited by 3
  13. 2024NeurCAM: Interpretable Neural Clustering via Additive Modelscited by 3
  14. 2025Additive Models Explained: A Computational Complexity Approachcited by 3
  15. 2022Topological Representations of Local Explanationscited by 2
  16. 2023Interpretable Predictive Models to Understand Risk Factors for Maternal and Fetal Outcomescited by 2
  17. 2024ProtoNAM: Prototypical Neural Additive Models for Interpretable Deep Tabular Learningcited by 2
  18. 2024Transparent Networks for Multivariate Time Seriescited by 2
  19. 2025Challenges in interpretability of additive modelscited by 2
  20. 2025Interpretable Multimodal Learning for Tumor Protein-Metal Binding: Progress, Challenges, and Perspectivescited by 1
  21. 2021Extracting Expert's Goals by What-if Interpretable Modelingcited by 0
  22. 2021A Unified and Fast Interpretable Model for Predictive Analyticscited by 0
  23. 2022Inherent Inconsistencies of Feature Importancecited by 0
  24. 2022A Concept and Argumentation based Interpretable Model in High Risk Domainscited by 0
  25. 2023SurvBeNIM: The Beran-Based Neural Importance Model for Explaining the Survival Modelscited by 0
  26. 2024FAST: An Optimization Framework for Fast Additive Segmentation in Transparent MLcited by 0
  27. 2024Quantifying Visual Properties of GAM Shape Plots: Impact on Perceived Cognitive Load and Interpretabilitycited by 0
  28. 2025Empowering Decision Trees via Shape Function Branchingcited by 0
  29. 2025Approximating Human Preferences Using a Multi-Judge Learned Systemcited by 0
  30. 2026Neural Additive Experts: Context-Gated Experts for Controllable Model Additivitycited by 0
  31. 2026Sequential Counterfactual Inference for Temporal Clinical Data: Addressing the Time Traveler Dilemmacited by 0
  32. 2026Complexity-Budgeted, Interaction-Aware Interpretable Model for Tabular Datacited by 0