# Are we measuring trust correctly in explainability, interpretability, and transparency research?

arXiv: https://arxiv.org/abs/2209.00651 · HTML: https://mlsanity.com/paper/2209.00651/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 28 references that are in the map.
- First posted on arXiv 31 Aug 2022.

## Builds on (most cited first, 4 of 4)

- [Metrics for Explainable AI: Challenges and Prospects](https://mlsanity.com/paper/1812.04608/) (2018)
- [Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI](https://mlsanity.com/paper/2010.07487/) (2020)
- [Quantifying Interpretability and Trust in Machine Learning Systems](https://mlsanity.com/paper/1901.08558/) (2019)
- [Local and Global Explanations of Agent Behavior: Integrating Strategy Summaries with Saliency Maps](https://mlsanity.com/paper/2005.08874/) (2020)

## Built on by (most cited first, 11 of 11)

- ["Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interaction](https://mlsanity.com/paper/2210.03735/) (2022)
- [A Systematic Review on Fostering Appropriate Trust in Human-AI Interaction](https://mlsanity.com/paper/2311.06305/) (2023)
- [GANterfactual-RL: Understanding Reinforcement Learning Agents' Strategies through Visual Counterfactual Explanations](https://mlsanity.com/paper/2302.12689/) (2023)
- [Humans, AI, and Context: Understanding End-Users' Trust in a Real-World Computer Vision Application](https://mlsanity.com/paper/2305.08598/) (2023)
- [Experiential Explanations for Reinforcement Learning](https://mlsanity.com/paper/2210.04723/) (2022)
- [Trust and Transparency in Recommender Systems](https://mlsanity.com/paper/2304.08094/) (2023)
- [Visualization for Recommendation Explainability: A Survey and New Perspectives](https://mlsanity.com/paper/2305.11755/) (2023)
- [Evolutionary Computation and Explainable AI: A Roadmap to Understandable Intelligent Systems](https://mlsanity.com/paper/2406.07811/) (2024)
- [Measuring Perceived Trust in XAI-Assisted Decision-Making by Eliciting a Mental Model](https://mlsanity.com/paper/2307.11765/) (2023)
- [Improving understanding and trust in AI: How users benefit from interval-based counterfactual explanations](https://mlsanity.com/paper/2604.09573/) (2026)
- [Investigating the Effects of Different Levels of User Control in an Interactive Educational Recommender System](https://mlsanity.com/paper/2605.01400/) (2026)

## Abstract (arXiv)

This paper presents an argument for why we are not measuring trust sufficiently in explainability, interpretability, and transparency research. Most studies ask participants to complete a trust scale to rate their trust of a model that has been explained/interpreted. If the trust is increased, we consider this a positive. However, there are two issues with this. First, we usually have no way of knowing whether participants should trust the model. Trust should surely decrease if a model is of poor quality. Second, these scales measure perceived trust rather than demonstrated trust. This paper showcases three methods that do a good job at measuring perceived and demonstrated trust. It is intended to be starting point for discussion on this topic, rather than to be the final say. The author invites critique and discussion.