Responsibility: An Example-based Explainable AI approach via Training Process Inspection
Not on the map. Why?
Abstract (arXiv)
Explainable Artificial Intelligence (XAI) methods are intended to help human users better understand the decision making of an AI agent. However, many modern XAI approaches are unintuitive to end users, particularly those without prior AI or ML knowledge. In this paper, we present a novel XAI approach we call Responsibility that identifies the most responsible training example for a particular decision. This example can then be shown as an explanation: "this is what I (the AI) learned that led me to do that". We present experimental results across a number of domains along with the results of an Amazon Mechanical Turk user study, comparing responsibility and existing XAI methods on an image classification task. Our results demonstrate that responsibility can help improve accuracy for both human end users and secondary ML models.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 29 of its 62 references that are in the map. First posted on arXiv 7 Sep 2022.
Builds on
29 of 62 references.
References · 29
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2017Axiomatic Attribution for Deep Networkscited by 3,350
- 2015Learning Deep Features for Discriminative Localizationcited by 2,430
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
- 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
- 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
- 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
17 more
- 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 617
- 2020Questioning the AI: Informing Design Practices for Explainable AI User Experiencescited by 251
- 2018Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learningcited by 203
- 2018Representer Point Selection for Explaining Deep Neural Networkscited by 187
- 2020Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systemscited by 138
- 2020Evaluating Explanations: How much do explanations from the teacher aid students?cited by 94
- 2020Evaluating Saliency Map Explanations for Convolutional Neural Networks: A User Studycited by 86
- 2020Explainable Artificial Intelligence: a Systematic Reviewcited by 79
- 2018iNNvestigate neural networks!cited by 58
- 2018What can AI do for me: Evaluating Machine Learning Interpretations in Cooperative Playcited by 52
- 2018Interpreting Black Box Predictions using Fisher Kernelscited by 48
- 2020How Useful Are the Machine-Generated Interpretations to General Users? A Human Evaluation on Guessing the Incorrectly Predicted Labelscited by 39
- 2020Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Predictioncited by 36
- 2019Regularizing Black-box Models for Improved Interpretabilitycited by 35
- 2017On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysiscited by 15
- 2021Sanity Simulations for Saliency Methodscited by 15
- 2020Explainability via Responsibilitycited by 2
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.