Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economics

TL;DR

This paper introduces a persona-based bias adjustment method for large language models to better simulate human decision-making, using behavioral economics data to improve alignment with real human responses in the ultimatum game.

Contribution

The paper presents a novel approach that leverages individual behavioral data to calibrate LLM biases, enhancing their ability to mimic human decision patterns.

Findings

Improved alignment with empirical human behavior in the ultimatum game.

Persona-conditioned LLMs better reflect population-level decision diversity.

Demonstrates potential for scalable human-like decision simulation.

Abstract

Large language models (LLMs) are increasingly used to simulate human decision-making, but their intrinsic biases often diverge from real human behavior--limiting their ability to reflect population-level diversity. We address this challenge with a persona-based approach that leverages individual-level behavioral data from behavioral economics to adjust model biases. Applying this method to the ultimatum game--a standard but difficult benchmark for LLMs--we observe improved alignment between simulated and empirical behavior, particularly on the responder side. While further refinement of trait representations is needed, our results demonstrate the promise of persona-conditioned LLMs for simulating human-like decision patterns at scale.