Human Misperception of Generative-AI Alignment: A Laboratory Experiment
Not on the map. Why?
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.
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
8 of 53 references.
References · 8
- 2020Artificial Intelligence, Values and Alignmentcited by 448
- 2019The Algorithmic Automation Problem: Prediction, Triage, and Human Effortcited by 101
- 2024Algorithmic Collusion by Large Language Modelscited by 62
- 2024Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Functioncited by 24
- 2022Artificial Intelligence and Auction Designcited by 20
- 2022Learning When to Advise Human Decision Makerscited by 18
- 2025Distributive Fairness in Large Language Models: Evaluating Alignment with Human Valuescited by 9
- 2025AI-Assisted Decision Making with Human Learningcited by 6
Built on by
Citing papers per year: 2025: 2; 2026: 2.
4 papers.
- 2026Strategic Algorithmic Monoculture: Experimental Evidence from Coordination Gamescited by 7
- 2025The Variance Paradox: How AI Reduces Diversity but Increases Noveltycited by 1
- 2025Morality is Contextual: Learning Interpretable Moral Contexts from Human Data with Probabilistic Clustering and Large Language Modelscited by 1
- 2026Learning to Decide with AI Assistance under Human-Alignmentcited by 1
- 2026Learning to Decide with AI Assistance under Human-Alignment12 May 2026
- 2026Strategic Algorithmic Monoculture: Experimental Evidence from Coordination Games10 Apr 2026
- 2025Morality is Contextual: Learning Interpretable Moral Contexts from Human Data with Probabilistic Clustering and Large Language Models24 Dec 2025
- 2025The Variance Paradox: How AI Reduces Diversity but Increases Novelty20 Aug 2025