Tell me more?: the effects of mental model soundness on personalizing an intelligent agent

By Todd Kulesza, Simone Stumpf, Margaret M. Burnett, Irwin Kwan. 2012

290 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

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

In Artificial Intelligence

In Signal Processing

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, methodology): “…of researchers have focused more specifically on explanations that might be presented to non-developer users of the systems (Hendricks et al., 2016; Kulesza et al, 2012; 2015; Lomas et al., 2012; Park et al., 2016; Ribiero et al., 2016; Rosenthal et al., 2016) This third generation is typified by…”
Do explanations make VQA models more predictable to a human? (2018, background): “or helping them achieve an end goal (Narayanan et al., 2018; Kulesza et al., 2012).”
Updates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff (2019, background): “Just as for other automated systems, humans create a mental model of AI agents (Kulesza et al. 2012).”
Power to the People: The Role of Humans in Interactive Machine Learning (2014, background): “In a recent study, Kulesza et al. (2012) provided users of a content-based music recommender with a 15-minute tutorial discussing how the recommender worked and how the various feedback controls (e.g., rating songs, steering towards specific feature values, etc.) would impact the learner.”
Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies (2021, methodology): “Some studies have explored improving the user agency, such as allowing and incorporating user feedback on predictions or personalization of the model [43, 76, 125].”
AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap (2023, background): “It may therefore be appropriate for evaluations of transparency approaches to incorporate assessments of mental model accuracy and completeness, for example by analyzing people’s comments or answers to questions about their beliefs about a model or application’s function and structure [48, 61, 67, 1”
F1 Is Not Enough! Models and Evaluation towards User-Centered Explainable Question Answering (2020, background): “…in self-reports with five-point Likert scales: certainty of the participants (Greis et al., 2017a), completeness and helpfulness of the explanations (Nourani et al., 2019), trust of the participants in the model (Bussone et al., 2015), and satisfaction (Kulesza et al., 2012; Greis et al., 2017b).”
Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda (2018, background): “With the increasing use of machine learning, Intelligent User Interfaces began to focus on providing explanations to debug learned models [100, 101, 162].”
Beyond Accuracy: The Role of Mental Models in Human-AI Team Performance (2019, background): “People create mental models for any system they interact with (Norman 1988), including AI agents (Kulesza et al. 2012).”
Principles of Explanatory Debugging to Personalize Interactive Machine Learning (2015, background): “To help users build useful mental models of the learning system, these explanations should observe the following principles: Research has suggested that users may best personalize a learning system if they build their mental models while interacting with it [23].”
A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems (2018, background): “res Work Mitigation Reliance ency eness Visualization ction uning ction Debugging etability del and Satisfaction rust Reliance 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] ◆ ”
Debugging Machine Learning Models (2016, background): “Systems such as Amershi et al. (2014) and Kulesza et al. (2012) are designed to bridge the gap between detecting errors and making improvements .”
No Explainability without Accountability: An Empirical Study of Explanations and Feedback in Interactive ML (2020, background): “Relationship of Explainability and Interactivity in ML Users need to understand how models work [23, 5, 34] to best fix them, and how models are explained changes user feedback [52, 33].”
Too much, too little, or just right? Ways explanations impact end users' mental models (2013, background): “As with other kinds of end-user debugging, users’ mental models of how an agent works help them decide exactly what about the agent they need to correct, and how to go about it [11].”
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].”
Explainability fact sheets: a framework for systematic assessment of explainable approaches (2019, background): “, deep, in which case they have a detailed understanding of how and why something works [27].”