# Behavioral Economics of AI: LLM Biases and Corrections

arXiv: https://arxiv.org/abs/2602.09362 · HTML: https://mlsanity.com/paper/2602.09362/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Feb 2026.

## Built on by (most cited first, 9 of 9)

- [Language Models Exhibit Inconsistent Biases Towards Algorithmic Agents and Human Experts](https://mlsanity.com/paper/2602.22070/) (2026)
- [LLM Consumer Behavior Theory: Foundations of a Novel Research Field](https://mlsanity.com/paper/2606.18005/) (2026)
- [Cognitive Convergence: Deep Similarities Between Large Language Models and Human Cognition](https://mlsanity.com/paper/2607.26179/) (2026)
- [From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models](https://mlsanity.com/paper/2608.06020/) (2026)
- [Your AI, On a Dial: Controlling Investment Bias in LLMs with a Single Neuron](https://mlsanity.com/paper/2608.22852/) (2026)
- [The Internal Anatomy of Strategic Choice in Large Language Models](https://mlsanity.com/paper/2609.07478/) (2026)
- [Do LLMs Choose Like Humans? Using Cognitive Theory to Evaluate LLM Decision-Making](https://mlsanity.com/paper/2609.22225/) (2026)
- [LLM sequential decision making under uncertainty in biochemical domains](https://mlsanity.com/paper/2609.33061/) (2026)
- [Behavioral History Outperforms Descriptions of the Person for LLM Synthetic Personas](https://mlsanity.com/paper/2610.03998/) (2026)

## Abstract (arXiv)

Do generative AI models, particularly large language models (LLMs), exhibit systematic behavioral biases in economic and financial decisions? If so, how can these biases be mitigated? Drawing on the cognitive psychology and experimental economics literatures, we conduct the most comprehensive set of experiments to date-originally designed to document human biases-on prominent LLM families across model versions and scales. We document systematic patterns in LLM behavior. In preference-based tasks, responses become more human-like as models become more advanced or larger, while in belief-based tasks, advanced large-scale models frequently generate rational responses. Prompting LLMs to make rational decisions reduces biases.