Intelligible Artificial Intelligence

By Daniel S. Weld, Gagan Bansal. 2018

35 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Algorithms at Work: The New Contested Terrain of Control (2020, methodology): “(2015),Orlikowski&Scott(2014b),Pasquale(2015),Weld&Bansal(2018) Technical literacy Machine-learning opacity 2020 multiple parties (Amershi, Cakmak, Knox, & Kulesza, 2014; Cambo & Gergle, 2018; Chalmers & MacColl, 2003).”
Expectation vs. Experience: Evaluating the Usability of Code Generation Tools Powered by Large Language Models (2022, background): “Prior studies have examined how users interact with imperfect AI [11, 23, 26–28, 35, 37, 45].”
Gamut: A Design Probe to Understand How Data Scientists Understand Machine Learning Models (2019, background): “Since then, interactive visual analytics has succeeded in supporting machine learning tasks [25, 41, 42, 55, 63].”
Software Engineering for Machine Learning: A Case Study (2019, background): “Several survey respondents and the larger Explainable AI community [32], [33] propose to use more interpretable models, or to develop visualization techniques that make black-box models more interpretable.”
One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques (2019, background): “There is comparatively much less work in the other two categories, notwithstanding calls for interactive explanation [32, 42, 61], and we hope that the taxonomy inspires more research in those directions.”
Explaining Decision-Making Algorithms through UI: Strategies to Help Non-Expert Stakeholders (2019, background): “We adapt Weld and Bansal (2018)’s definition that a human user “understands” the al-gorithm if the human can see what attributes cause the algorithm’s action and can predict how changes in the situation can lead to alternative algorithm predictions .”
Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers (2018, unknown): “Another interesting area for how deep learning visualization is used makes heavy use of interactions [85] for experimenting with models.”
Using Machine Learning Safely in Automotive Software: An Assessment and Adaption of Software Process Requirements in ISO 26262 (2018, background): “[73] Weld, D.S., and G. Bansal.”
Will You Accept an Imperfect AI?: Exploring Designs for Adjusting End-user Expectations of AI Systems (2019, background): “However, the shift to deep learning models in many end-user applications makes it practically infeasible to apply many intelligibility types proposed in earlier work [51].”