Are explanations always important?: a study of deployed, low-cost intelligent interactive systems

By Andrea Bunt, Matthew Lount, Catherine Lauzon. 2012

119 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

Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) (2018, background): “[160] raised questions as to the importance of, and consequently anticipated usage of, explanation techniques within systems that support users in making low-cost decisions.”
Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence (2023, background): “In the spirit of holism, Bunt et al. [92] originally raised this question in their work mainly due to the efficiency of explanation techniques deployed in systems that offer users low-cost decisions.”
Will You Accept an Imperfect AI?: Exploring Designs for Adjusting End-user Expectations of AI Systems (2019, background): “Most proposed approaches also require significant end-user interest and effort in understanding system behavior, which can be inefficient in many scenarios [7].”
A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems (2018, methodology): “iance AI Performance es Herlocker et al. 2000 [77] ◆ ◆ ◆ ◆ Kulesza et al. 2012 [109] ◆ ◆ ◆ ◆ Lim et al. 2009 [124] ◆ ◆ ◆ Stumpf et al. 2018 [195] ◆ ◆ ◆ ◆ Bilgic et al. 2005[19] ◆ ◆ ◆ Bunt et al. 2012 [25] ◆ ◆ Gedikli et al. 2014 [62] ◆ ◆ Kulesza et al. 2013 [111] ◆ ◆ ◆ ◆ Lim et al. 2009 [125] ◆ ◆ ◆ ”
Trustworthy Artificial Intelligence: A Review (2022, background): “F, A [22, 171, 226] F, E [14, 179] E, A [75, 108, 186, 206] F, E, A, P, Ac [92] F, E, A, Ac [134] F, Ac [26] A, P, Ac [163, 214] E, A [55, 132] A, Ac [25, 29, 105, 113, 157, 159, 168, 197] F, A, Ac [111, 174] Ac [204]”
User Trust in Intelligent Systems: A Journey Over Time (2016, methodology): “The effect of explanations on user trust has been examined using existing methods [1, 12, 16].”
Progressive Disclosure: Designing for Effective Transparency (2018, background): “This is also demonstrated this in the context of Google search suggestions; where users felt the cost of processing explanations outweighed their benefits [12].”
The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies (2020, background): “sufficiently, the cost of explanation may outweigh the benefit [34].”
Principles of Explanatory Debugging to Personalize Interactive Machine Learning (2015, background): “Research suggests that to elicit corrections from users, this feedback mechanism should embody the following principles: Principle 2.1: Be Actionable Both theory [3] and prior empirical ﬁndings [6, 23, 25] suggest end users will ignore explanations when the beneﬁt of attending to them is unclear.”
Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions (2023, background): “Furthermore, concept-based explanations could help combat adversarial attacks, especially a recent form of such attacks that aim to trick both humans and classifiers [162].”
Evaluating the Quality of Learning Resources: A Learnersourcing Approach (2021, background): “While some studies suggest that explainable AI (XIA) [67] is not always required [68], the use of black-box outcomes seems to be inadequate for educational settings where educators strive to enable students to develop their own vision, reasoning, and appreciation for inquiry and investigation, and…”
Too much, too little, or just right? Ways explanations impact end users' mental models (2013, background): “For example, Bunt et al. [2] found that when users had no direct control over an agent’s reasoning, user interest in any type of explanation was very low.”