arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.03299cs.AIcs.CL
收藏

好、坏与绿巨人般的GPT:分析大型语言模型在合作与议价博弈中的情感决策

The Good, the Bad, and the Hulk-like GPT: Analyzing Emotional Decisions of Large Language Models in Cooperation and Bargaining Games

AIRI;NUST MISIS(国立研究型技术大学 MISIS);HSE University(高等经济大学);Cornell University(康奈尔大学);SPbU(圣彼得堡大学)

Mikhail Mozikov, Nikita Severin, Valeria Bodishtianu, Maria Glushanina, Mikhail Baklashkin, Andrey V. Savchenko, Ilya Makarov

AI总结:

本文提出一种研究大型语言模型在情感状态下决策及与人类行为一致性的新框架,发现在合作与议价博弈中情感深刻影响GPT-3.5和GPT-4的表现,且“愤怒”情感提示能打破GPT-4的理性一致性。

摘要:

行为研究实验是社会建模和理解人类互动的重要组成部分。在实践中,由于人类社会研究中社会互动与合作的复杂性,许多行为实验在内部和外部有效性、可重复性以及社会偏见方面面临挑战。大型语言模型(LLMs)的最新进展为研究人员提供了一种用于模拟人类行为的全新且极具前景的工具。然而,现有的基于LLM的模拟在未经证实的假设下运行,即假设LLM智能体的行为与人类相似,同时忽略了人类决策中的一个关键因素:情感。在本文中,我们引入了一种新颖的方法论和框架,以同时研究LLMs的决策及其在情感状态下与人类行为的一致性。在两类行为博弈论的四个博弈中对GPT-3.5和GPT-4进行的实验表明,情感深刻影响了LLMs的表现,促使其发展出更优的策略。GPT-3.5的行为反应与人类参与者之间存在强烈的一致性,在议价博弈中尤为明显;而GPT-4则表现出一致的行为,在理性决策中忽略被诱导的情感。令人惊讶的是,情感提示,尤其是使用“愤怒”情感时,能够打破GPT-4“超人类”的一致性,使其表现出类似人类的情感反应。

英文摘要:

Behavior study experiments are an important part of society modeling and understanding human interactions. In practice, many behavioral experiments encounter challenges related to internal and external validity, reproducibility, and social bias due to the complexity of social interactions and cooperation in human user studies. Recent advances in Large Language Models (LLMs) have provided researchers with a new promising tool for the simulation of human behavior. However, existing LLM-based simulations operate under the unproven hypothesis that LLM agents behave similarly to humans as well as ignore a crucial factor in human decision-making: emotions. In this paper, we introduce a novel methodology and the framework to study both, the decision-making of LLMs and their alignment with human behavior under emotional states. Experiments with GPT-3.5 and GPT-4 on four games from two different classes of behavioral game theory showed that emotions profoundly impact the performance of LLMs, leading to the development of more optimal strategies. While there is a strong alignment between the behavioral responses of GPT-3.5 and human participants, particularly evident in bargaining games, GPT-4 exhibits consistent behavior, ignoring induced emotions for rationality decisions. Surprisingly, emotional prompting, particularly with `anger' emotion, can disrupt the "superhuman" alignment of GPT-4, resembling human emotional responses.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑