Toward establishing trust in adaptive agents

By Alyssa Glass, Deborah L. McGuinness, Michael Wolverton. 2008

253 citations recorded by the source corpus.

Subfields: Experimental and Cognitive Psychology, Information Systems and Management, Management Science and Operations Research

How researchers see this paper

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

In Experimental and Cognitive Psychology

In Information Systems and Management

In Management Science and Operations Research

Citations in the corpus

In AI We Trust? Factors That Influence Trustworthiness of AI-infused Decision-Making Processes (2019, background): “Work by Glass et al. [13] suggests that availability of explanations is an important aspect for establishing trust of an intelligent agent.”
Manipulating and Measuring Model Interpretability (2018, methodology): “We therefore take a human-centered approach, building on previous psychology and social science research on human trust in models [4, 17, 21] and similar efforts in the machine learning and human-computer interaction communities [2, 6, 8, 13, 15, 23, 24].”
Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda (2018, background): “Domains include recommenders [33], decision support [62], medical [19, 99], business processes [88, 98], e-commerce [164, 186], social networks [63, 161], smart sensors [112, 113], smart homes [2, 30, 183], games [134, 182], and public displays [179].”
Questioning the AI: Informing Design Practices for Explainable AI User Experiences (2020, background): “[35] investigated users’ explanation requirements in using an adaptive agent and showed that user needs for different types of explanation vary.”
Assessing demand for intelligibility in context-aware applications (2009, background): “McGuinness and colleagues [14, 21] have identified information need factors that influence the level of trust in adaptive agents.”
You Are the Only Possible Oracle: Effective Test Selection for End Users of Interactive Machine Learning Systems (2014, background): “ating explanations, researchers have also investigated the types of information users want before assessing the trustworthiness of a classifier [19], [33].”
Explanatory Debugging: Supporting End-User Debugging of Machine-Learned Programs (2010, background): “Prior research [6, 20] has shown that users want to understand this logic.”
Mini-crowdsourcing end-user assessment of intelligent assistants: A cost-benefit study (2011, background): “As a basis for creating explanations, researchers have also investigated the types of information users want before assessing the trustworthiness of an intelligent agent [4, 11].”
Interactive and interpretable machine learning models for human machine collaboration (2015, background): “Communication with the user is essential to a successful interactive system — it improves transparency, which has been identified as a major factor in establishing user trust in adaptive agents [111, 58] and improving system acceptance [68, 127].”
Explainable Reinforcement Learning: A Survey (2020, background): “Trust is an essential prerequisite of using a model or system [26, 12], and transparency has been identified as one key component both in increasing users’ trust [18], as well as users’ acceptance of a system [24] (for a formal definition of transparency and related terms, see section 1.”
Interacting meaningfully with machine learning systems: Three experiments (2009, background): “There is some evidence that transparency via explanations is a major factor towards establishing trust in adaptive agents (Glass et al. 2008; Pazzani 2000).”
Where Are My Intelligent Assistant's Mistakes? A Systematic Testing Approach (2011, unknown): “In our approach (WYSIWYT/ML), the system (1) advises the user about which predictions to test, then (2) contributes more tests “like” the user’s, (3) measures how much of the assistant’s reasoning has been tested, and (4) continually monitors over time whether previous testing still “covers” new…”
How Much Information?: Effects of Transparency on Trust in an Algorithmic Interface (2016, background): “In a qualitative study of factors influencing trust in a complex adaptive agent, system transparency emerged as a core theme in user interviews [8].”
Human Trust in Artificial Intelligence: Review of Empirical Research (2020, background): “Glass, McGuinness, and Wolverton (2008) interviewed users of an office assistant agent and found that correct expectations regarding the agent ’ s performance and capabilities facilitated trust in the agent.”
Are explanations always important?: a study of deployed, low-cost intelligent interactive systems (2012, background): “[6] performed a field study evaluating information needs and perceptions of trust of the CALO system, a complex task assistant for a range of office-related tasks.”
A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems (2018, background): “Also, to better understand factors that influence trust in adaptive agents, Glass et al. [65] studied which types of questions users would like to be able to ask an adaptive assistant.”
iBCM: Interactive Bayesian Case Model Empowering Humans via Intuitive Interaction (2015, background): “Communication with the user is essential to a successful interactive system — it improves transparency, which has been identified as a major factor in establishing user trust in adaptive agents [28, 13] and improving system acceptance [17, 30].”