# Underspecified Human Decision Experiments Considered Harmful

arXiv: https://arxiv.org/abs/2401.15106 · HTML: https://mlsanity.com/paper/2401.15106/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 71 references that are in the map.
- First posted on arXiv 25 Jan 2024.

## Builds on (most cited first, 21 of 21)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?](https://mlsanity.com/paper/2005.01831/) (2020)
- [To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making](https://mlsanity.com/paper/2102.09692/) (2021)
- [Human-Centered Tools for Coping with Imperfect Algorithms during Medical Decision-Making](https://mlsanity.com/paper/1902.02960/) (2019)
- [Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies](https://mlsanity.com/paper/2112.11471/) (2021)
- [Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making](https://mlsanity.com/paper/2101.05303/) (2021)
- [Do Explanations make VQA Models more Predictable to a Human?](https://mlsanity.com/paper/1810.12366/) (2018)
- [Teaching Humans When To Defer to a Classifier via Exemplars](https://mlsanity.com/paper/2111.11297/) (2021)
- [Optimization of Scoring Rules](https://mlsanity.com/paper/2007.02905/) (2020)
- [Human-Aligned Calibration for AI-Assisted Decision Making](https://mlsanity.com/paper/2306.00074/) (2023)
- [Leveraging Rationales to Improve Human Task Performance](https://mlsanity.com/paper/2002.04202/) (2020)
- [Sibyl: Understanding and Addressing the Usability Challenges of Machine Learning In High-Stakes Decision Making](https://mlsanity.com/paper/2103.02071/) (2021)
- [Human Evaluation of Spoken vs. Visual Explanations for Open-Domain QA](https://mlsanity.com/paper/2012.15075/) (2020)
- [The Impact of Algorithmic Risk Assessments on Human Predictions and its Analysis via Crowdsourcing Studies](https://mlsanity.com/paper/2109.01443/) (2021)
- [When Does Uncertainty Matter?: Understanding the Impact of Predictive Uncertainty in ML Assisted Decision Making](https://mlsanity.com/paper/2011.06167/) (2020)
- [Do I Look Like a Criminal? Examining how Race Presentation Impacts Human Judgement of Recidivism](https://mlsanity.com/paper/2002.01111/) (2020)
- [The Rational Agent Benchmark for Data Visualization](https://mlsanity.com/paper/2304.03432/) (2023)
- [A Bayesian Cognition Approach to Improve Data Visualization](https://mlsanity.com/paper/1901.02949/) (2019)
- [Bayesian-Assisted Inference from Visualized Data](https://mlsanity.com/paper/2008.00142/) (2020)
- [Designing Shared Information Displays for Agents of Varying Strategic Sophistication](https://mlsanity.com/paper/2310.10858/) (2023)

## Built on by (most cited first, 1 of 1)

- [Trust Hinders Bidirectional Human-AI Alignment](https://mlsanity.com/paper/2610.15136/) (2026)

## Abstract (arXiv)

Decision-making with information displays is a key focus of research in areas like human-AI collaboration and data visualization. However, what constitutes a decision problem, and what is required for an experiment to conclude that decisions are flawed, remain imprecise. We present a widely applicable definition of a decision problem synthesized from statistical decision theory and information economics. We claim that to attribute loss in human performance to bias, an experiment must provide the information that a rational agent would need to identify the normative decision. We evaluate whether recent empirical research on AI-assisted decisions achieves this standard. We find that only 10 (26%) of 39 studies that claim to identify biased behavior presented participants with sufficient information to make this claim in at least one treatment condition. We motivate the value of studying well-defined decision problems by describing a characterization of performance losses they allow to be conceived.