# An Empirical Evaluation of Predicted Outcomes as Explanations in Human-AI Decision-Making

arXiv: https://arxiv.org/abs/2208.04181 · HTML: https://mlsanity.com/paper/2208.04181/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Aug 2022.

## Built on by (most cited first, 7 of 7)

- [Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanations](https://mlsanity.com/paper/2302.02187/) (2023)
- [Human-AI collaboration is not very collaborative yet: A taxonomy of interaction patterns in AI-assisted decision making from a systematic review](https://mlsanity.com/paper/2310.19778/) (2023)
- [AI Reliance and Decision Quality: Fundamentals, Interdependence, and the Effects of Interventions](https://mlsanity.com/paper/2304.08804/) (2023)
- [A Survey of AI Reliance](https://mlsanity.com/paper/2408.03948/) (2024)
- [Human in the Latent Loop (HILL): Interactively Guiding Model Training Through Human Intuition](https://mlsanity.com/paper/2505.06325/) (2025)
- [The Effect of Explainable AI-based Decision Support on Human Task Performance: A Meta-Analysis](https://mlsanity.com/paper/2504.13858/) (2025)
- [Six Guidelines for Trustworthy, Ethical and Responsible Automation Design](https://mlsanity.com/paper/2508.02371/) (2025)

## Abstract (arXiv)

In this work, we empirically examine human-AI decision-making in the presence of explanations based on predicted outcomes. This type of explanation provides a human decision-maker with expected consequences for each decision alternative at inference time - where the predicted outcomes are typically measured in a problem-specific unit (e.g., profit in U.S. dollars). We conducted a pilot study in the context of peer-to-peer lending to assess the effects of providing predicted outcomes as explanations to lay study participants. Our preliminary findings suggest that people's reliance on AI recommendations increases compared to cases where no explanation or feature-based explanations are provided, especially when the AI recommendations are incorrect. This results in a hampered ability to distinguish correct from incorrect AI recommendations, which can ultimately affect decision quality in a negative way.