# Measure Utility, Gain Trust: Practical Advice for XAI Researcher

arXiv: https://arxiv.org/abs/2009.12924 · HTML: https://mlsanity.com/paper/2009.12924/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2020.

## Built on by (most cited first, 9 of 9)

- [Use-Case-Grounded Simulations for Explanation Evaluation](https://mlsanity.com/paper/2206.02256/) (2022)
- [Impact Of Explainable AI On Cognitive Load: Insights From An Empirical Study](https://mlsanity.com/paper/2304.08861/) (2023)
- [Let's Go to the Alien Zoo: Introducing an Experimental Framework to Study Usability of Counterfactual Explanations for Machine Learning](https://mlsanity.com/paper/2205.03398/) (2022)
- [How explainable AI affects human performance: A systematic review of the behavioural consequences of saliency maps](https://mlsanity.com/paper/2404.16042/) (2024)
- [Are Metrics Enough? Guidelines for Communicating and Visualizing Predictive Models to Subject Matter Experts](https://mlsanity.com/paper/2205.05749/) (2022)
- [Utility Theory based Cognitive Modeling in the Application of Robotics: A Survey](https://mlsanity.com/paper/2306.09445/) (2023)
- [Human-centered trust framework: An HCI perspective](https://mlsanity.com/paper/2305.03306/) (2023)
- [A Case Study on Designing Evaluations of ML Explanations with Simulated User Studies](https://mlsanity.com/paper/2302.07444/) (2023)
- [Challenges and Trends in User Trust Discourse in AI](https://mlsanity.com/paper/2305.11876/) (2023)

## Abstract (arXiv)

Research into the explanation of machine learning models, i.e., explainable AI (XAI), has seen a commensurate exponential growth alongside deep artificial neural networks throughout the past decade. For historical reasons, explanation and trust have been intertwined. However, the focus on trust is too narrow, and has led the research community astray from tried and true empirical methods that produced more defensible scientific knowledge about people and explanations. To address this, we contribute a practical path forward for researchers in the XAI field. We recommend researchers focus on the utility of machine learning explanations instead of trust. We outline five broad use cases where explanations are useful and, for each, we describe pseudo-experiments that rely on objective empirical measurements and falsifiable hypotheses. We believe that this experimental rigor is necessary to contribute to scientific knowledge in the field of XAI.