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

2025/08/26 by Kitadai, Ayato, Fukasawa, Yusuke, Nishino, Nariaki
#Computer Science and Game Theory (cs.GT) #FOS: Computer and information sciences #FOS: Economics and business #General Economics (econ.GN) #Multiagent Systems (cs.MA)

paper · doi:10.48550/arxiv.2508.18600

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.

Citations

• An Empirical Analysis on Large Language Models in Debate Evaluation
• Measuring Political Bias in Large Language Models: What Is Said and How It Is Said
• Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation
• Frontiers: Determining the Validity of Large Language Models for Automated Perceptual Analysis
• Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives
• Simulating Opinion Dynamics with Networks of LLM-based Agents
• Do LLMs exhibit human-like response biases? A case study in survey design
• EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities
• ChatDev: Communicative Agents for Software Development
• The Machine Psychology of Cooperation: Can GPT models operationalise prompts for altruism, cooperation, competitiveness and selfishness in economic games?
• PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits
• Generative Agents: Interactive Simulacra of Human Behavior
• Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?
• Out of One, Many: Using Language Models to Simulate Human Samples
• Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies
• Language (Technology) is Power: A Critical Survey of "Bias" in NLP
• Macroeconomics and Reality

Related

• Simulating Human Strategic Behavior: Comparing Single and Multi-agent LLMs
• Noise, Adaptation, and Strategy: Assessing LLM Fidelity in Decision-Making
• LLM-driven Imitation of Subrational Behavior : Illusion or Reality?
• Large language models replicate and predict human cooperation across experiments in game theory
• Computational Basis of LLM's Decision Making in Social Simulation