# Human Misperception of Generative-AI Alignment: A Laboratory Experiment

arXiv: https://arxiv.org/abs/2502.14708 · HTML: https://mlsanity.com/paper/2502.14708/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 53 references that are in the map.
- First posted on arXiv 20 Feb 2025.

## Builds on (most cited first, 8 of 8)

- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [The Algorithmic Automation Problem: Prediction, Triage, and Human Effort](https://mlsanity.com/paper/1903.12220/) (2019)
- [Algorithmic Collusion by Large Language Models](https://mlsanity.com/paper/2404.00806/) (2024)
- [Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Function](https://mlsanity.com/paper/2406.01382/) (2024)
- [Artificial Intelligence and Auction Design](https://mlsanity.com/paper/2202.05947/) (2022)
- [Learning When to Advise Human Decision Makers](https://mlsanity.com/paper/2209.13578/) (2022)
- [Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values](https://mlsanity.com/paper/2502.00313/) (2025)
- [AI-Assisted Decision Making with Human Learning](https://mlsanity.com/paper/2502.13062/) (2025)

## Built on by (most cited first, 4 of 4)

- [Strategic Algorithmic Monoculture: Experimental Evidence from Coordination Games](https://mlsanity.com/paper/2604.09502/) (2026)
- [The Variance Paradox: How AI Reduces Diversity but Increases Novelty](https://mlsanity.com/paper/2508.19264/) (2025)
- [Morality is Contextual: Learning Interpretable Moral Contexts from Human Data with Probabilistic Clustering and Large Language Models](https://mlsanity.com/paper/2512.21439/) (2025)
- [Learning to Decide with AI Assistance under Human-Alignment](https://mlsanity.com/paper/2605.12646/) (2026)

## Abstract (arXiv)

We conduct an incentivized laboratory experiment to study people's perception of generative artificial intelligence (GenAI) alignment in the context of economic decision-making. Using a panel of economic problems spanning the domains of risk, time preference, social preference, and strategic interactions, we ask human subjects to make choices for themselves and to predict the choices made by GenAI on behalf of a human user. We find that people overestimate the degree of alignment between GenAI and human choices. In every problem, human subjects' average prediction about GenAI's choice is substantially closer to the average human-subject choice than it is to the GenAI choice. At the individual level, different subjects' predictions about GenAI's choice in a given problem are highly correlated with their own choices in the same problem. We explore the implications of people overestimating GenAI alignment in a simple theoretical model.