Why and why not explanations improve the intelligibility of context-aware intelligent systems

By Brian Y. Lim, Anind K. Dey, Daniel Avrahami. 2009

686 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Information Systems and Management, Surgery, 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 Surgery

In Safety, Robustness & Interpretability

In Human-Computer Interaction

Citations in the corpus

Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, background): “Lim and Dey (2009, 2010); and Lim, Dey, and Avrahami (2009).”
Anchors: High-Precision Model-Agnostic Explanations (2018, background): “Compared to other interpretable options, rules fare well; users prefer, trust and understand rules better than alternatives (Lim, Dey, and Avrahami 2009; Stumpf et al. 2007), in particular rules similar to anchors.”
Explain Yourself: A Natural Language Interface for Scrutable Autonomous Robots (2018, background): “Lim et al. (2009) [10] show that both why and why not explanations increase understanding but only why increases trust.”
'It's Reducing a Human Being to a Percentage': Perceptions of Justice in Algorithmic Decisions (2018, background): “Inspired by different theoretical models of argumentation, various explanation types have been explored and tested, with the style of explanation provided affecting the extent to which end-users understand the decisions of expert systems [46, 39].”
Principles of Explanatory Debugging to Personalize Interactive Machine Learning (2015, background): “Other work has studied the impact of machine-generated explanations on users’ mental models, but did not explore whether this helped participants’ personalize their learning systems [8, 25, 30].”
Explainable Autonomy: A Study of Explanation Styles for Building Clear Mental Models (2018, background): “Lim et al. (2009) went on to investigate the ﬁrst two of these and showed that explaining why a system behaved a certain way increased both understanding and trust, whilst “ Why not ” showed only an increase in understanding.”
Progressive Disclosure: Designing for Effective Transparency (2018, background): “There are many other ways to depict how an algorithm operates including verbal explanations, concrete user exploration, and so forth [40,42,48,69].”
Toolkit to support intelligibility in context-aware applications (2010, background): “To counter this, it is important to make context-aware applications intelligible [5, 25, 26] by automatically providing explanations of application behavior.”
Explaining prediction models and individual predictions with feature contributions (2014, background): “Other studies focused only on decision trees [20] and on decision trees and decision rules [2].”
Explanations in Autonomous Driving: A Survey (2021, background): “causal filters or investigatory queries like why, why not, how to, and what if [60].”
Are Explanations Helpful? A Comparative Study of the Effects of Explanations in AI-Assisted Decision-Making (2021, background): “Earlier literature on AI explanations often concerns the communication of uncertainty in AI decisions [45, 46].”
Learning from a learning thermostat: lessons for intelligent systems for the home (2013, background): “been done into how to design interfaces that render system behavior more intelligible [1,12,24], such research has yet”
Working with Machines: The Impact of Algorithmic and Data-Driven Management on Human Workers (2015, background): “In most research on sensemaking and mental models of intelligent systems, the focus has been on individual sensemaking [20, 21, 24, 35, 43].”
F1 Is Not Enough! Models and Evaluation towards User-Centered Explainable Question Answering (2020, methodology): “We derive multiple dependent variables from the participants’ ratings, namely completion time (Lim et al., 2009; Lage et al., 2019), several performance variables indicating how well they judged the correctness of the model (fraction of correct ratings, false positive ratio (FP), false negative…”
Explainable Artificial Intelligence: a Systematic Review (2020, background): “In the experiment run in [346, 77], participants were invited to interact with a model that predicts whether a person is doing physical exercise or not,”
The Role of Explanations on Trust and Reliance in Clinical Decision Support Systems (2015, background): “…Engineering City University London London, United Kingdom Adrian.Bussone.1@city.ac.uk, Simone.Stumpf.1@city.ac.uk, Dympna.O'Sullivan.1@city.ac.uk Abstract— Clinical decision support systems (CDSS) are increasingly used by healthcare professionals for evidence-based diagnosis and treatment support.”