Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda

By Ashraf Abdul, Jo Vermeulen, Danding Wang, Brian Y. Lim, Mohan Kankanhalli. 2018

840 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Information Systems and Management, Management Information Systems, Safety, Robustness & Interpretability, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Information Systems and Management

In Management Information Systems

In Safety, Robustness & Interpretability

In Human-Computer Interaction

Citations in the corpus

Explaining Explanations: An Overview of Interpretability of Machine Learning (2018, methodology): “One previous review paper of explainable AI performed a sizable data-driven literature analysis of explainable systems [75].”
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) (2018, background): “Given HCI’s [61] core interest in technology that entails understanding and better empowering users, techniques from this research field can help in developing transparent systems.”
Towards Faithfully Interpretable NLP Systems: How Should We Define and Evaluate Faithfulness? (2020, background): “In the general case, the final evaluation metric is the performance of the user at their task (Abdul et al., 2018).”
Automated rationale generation: a technique for explainable AI and its effects on human perceptions (2019, background): “stinction between interpretability and explanation is that explanation does not elucidate precisely how a model works but aims to give useful information for practitioners and end users. Abdul et al. [2] conduct a comprehensive survey on trends in explainable and intelligible systems research. Our w”
A survey of algorithmic recourse: definitions, formulations, solutions, and prospects (2020, background): “For XAI, see [1, 2, 31, 55, 61, 67, 75, 111, 120, 128], for causal and counterfactual inference, see [63, 76, 131, 145, 146, 159, 185], and for optimization, see [32, 137, 166].”
A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems (2018, background): “ng process [69]. Others suggest a set of theoretical and design principles to support intelligibility of the system and accountability of human users (e.g., [51, 7]). In a recent survey, Abdul et al. [1] presented a thorough literature analysis to ﬁnd XAI related topics and the relationship between ”
RuleMatrix: Visualizing and Understanding Classifiers with Rules (2018, methodology): “Visualization has been increasingly used to support the understanding, diagnosis and refinement of machine learning models [1, 22].”
Causal Discovery with Attention-Based Convolutional Neural Networks (2019, background): “emerging field of explainable machine learning enables DNN interpretation [7].”