FairMindSim: Alignment of Behavior, Emotion, and Belief in Humans and LLM Agents Amid Ethical Dilemmas

TL;DR

FairMindSim, which simulates the moral dilemma through a series of unfair scenarios, is introduced and the Belief-Reward Alignment Behavior Evolution Model (BREM) based on the recursive reward model (RRM), which indicates that, behaviorally, GPT-4o exhibits a stronger sense of social justice, while humans display a richer range of emotions.

Abstract

AI alignment is a pivotal issue concerning AI control and safety. It should consider not only value-neutral human preferences but also moral and ethical considerations. In this study, we introduced FairMindSim, which simulates the moral dilemma through a series of unfair scenarios. We used LLM agents to simulate human behavior, ensuring alignment across various stages. To explore the various socioeconomic motivations, which we refer to as beliefs, that drive both humans and LLM agents as bystanders to intervene in unjust situations involving others, and how these beliefs interact to influence individual behavior, we incorporated knowledge from relevant sociological fields and proposed the Belief-Reward Alignment Behavior Evolution Model (BREM) based on the recursive reward model (RRM). Our findings indicate that, behaviorally, GPT-4o exhibits a stronger sense of social justice, while humans display a richer range of emotions. Additionally, we discussed the potential impact of emotions on behavior. This study provides a theoretical foundation for applications in aligning LLMs with altruistic values.

Figures (9)

• Figure 1: FairMindSim is a versatile framework designed to simulate decision-making scenarios that explore human and LLMs emotional responses and perceptions of fairness.
• Figure 2: Distribution scheme for players under different conditions.
• Figure 3: Belief-Reward Alignment Behavior Evolution Model Framework
• Figure 4: Rejection Rate in Different Groups.
• Figure 5: Distribution of Arousal and Valence in different groups.