Corpus ID: 3652280

How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation

  title={How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation},
  author={M. Narayanan and Emily Chen and Jeffrey He and Been Kim and Sam Gershman and Finale Doshi-Velez},
  • M. Narayanan, Emily Chen, +3 authors Finale Doshi-Velez
  • Published 2018
  • Computer Science, Mathematics
  • ArXiv
  • Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains poorly understood. This work advances our understanding of what makes explanations interpretable in the specific context of verification. Suppose we have a machine learning system that predicts X, and we provide rationale for this prediction X. Given an input… CONTINUE READING
    128 Citations

    Figures, Tables, and Topics from this paper

    What can AI do for me?: evaluating machine learning interpretations in cooperative play
    • 32
    • Highly Influenced
    • PDF
    What Would You Ask the Machine Learning Model? Identification of User Needs for Model Explanations Based on Human-Model Conversations
    • PDF
    Do explanations make VQA models more predictable to a human?
    • 22
    • PDF
    A Survey of Evaluation Methods and Measures for Interpretable Machine Learning
    • 47
    What is Interpretability
    • 1
    • PDF
    • Highly Influenced
    Evaluating Explanation Without Ground Truth in Interpretable Machine Learning
    • 19
    • PDF


    Towards A Rigorous Science of Interpretable Machine Learning
    • 1,176
    • PDF
    The Promise and Peril of Human Evaluation for Model Interpretability
    • 41
    • PDF
    Programs as Black-Box Explanations
    • 33
    • Highly Influential
    • PDF
    "Why Should I Trust You?": Explaining the Predictions of Any Classifier
    • 4,037
    • Highly Influential
    • PDF
    Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations
    • 196
    • PDF
    Interpretable Decision Sets: A Joint Framework for Description and Prediction
    • 345
    • Highly Influential
    • PDF
    The structure and function of explanations
    • T. Lombrozo
    • Psychology, Medicine
    • Trends in Cognitive Sciences
    • 2006
    • 385
    • PDF
    Rationalizing Neural Predictions
    • 390
    • Highly Influential
    • PDF