# Should We Trust (X)AI? Design Dimensions for Structured Experimental Evaluations

arXiv: https://arxiv.org/abs/2009.06433 · HTML: https://mlsanity.com/paper/2009.06433/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2020.

## Built on by (most cited first, 8 of 8)

- [Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies](https://mlsanity.com/paper/2112.11471/) (2021)
- [Trust in AI: Progress, Challenges, and Future Directions](https://mlsanity.com/paper/2403.14680/) (2024)
- [Unpacking Human-AI interactions: From interaction primitives to a design space](https://mlsanity.com/paper/2401.05115/) (2024)
- [Explanation as a process: user-centric construction of multi-level and multi-modal explanations](https://mlsanity.com/paper/2110.03759/) (2021)
- [Are We Closing the Loop Yet? Gaps in the Generalizability of VIS4ML Research](https://mlsanity.com/paper/2308.06290/) (2023)
- [Cultural Bias in Explainable AI Research: A Systematic Analysis](https://mlsanity.com/paper/2403.05579/) (2024)
- [Tell Me Something That Will Help Me Trust You: A Survey of Trust Calibration in Human-Agent Interaction](https://mlsanity.com/paper/2205.02987/) (2022)
- ["Even explanations will not help in trusting [this] fundamentally biased system": A Predictive Policing Case-Study](https://mlsanity.com/paper/2504.11020/) (2025)

## Abstract (arXiv)

This paper systematically derives design dimensions for the structured evaluation of explainable artificial intelligence (XAI) approaches. These dimensions enable a descriptive characterization, facilitating comparisons between different study designs. They further structure the design space of XAI, converging towards a precise terminology required for a rigorous study of XAI. Our literature review differentiates between comparative studies and application papers, revealing methodological differences between the fields of machine learning, human-computer interaction, and visual analytics. Generally, each of these disciplines targets specific parts of the XAI process. Bridging the resulting gaps enables a holistic evaluation of XAI in real-world scenarios, as proposed by our conceptual model characterizing bias sources and trust-building. Furthermore, we identify and discuss the potential for future work based on observed research gaps that should lead to better coverage of the proposed model.