人类交互是否可由生成式智能体复制？层级交互中代词使用的案例研究
Are Human Interactions Replicable by Generative Agents? A Case Study on Pronoun Usage in Hierarchical Interactions
AI总结：
本文研究LLM智能体在层级交互中的代词使用模式，发现其与人类存在显著差异，即使理解模式也无法在实际交互中复现，揭示了基于LLM的社会模拟的局限性。
摘要：
随着大语言模型（LLMs）能力的提升，研究人员越来越多地将其用于社会模拟。本文研究LLM智能体之间的交互是否与人类相似。具体而言，我们关注领导者与非领导者之间的代词使用差异，考察模拟是否会在LLMs的交互过程中产生类似人类的代词使用模式。我们的评估揭示了基于LLM的模拟与人类代词使用之间存在显著差异，基于提示或专门的智能体未能表现出类似人类的代词使用模式。此外，我们发现，即使LLMs理解人类的代词使用模式，它们在实际交互过程中也无法表现出来。我们的研究强调了基于LLM智能体的社会模拟的局限性，敦促从业者在决策过程中谨慎使用此类社会模拟。
英文摘要：
As Large Language Models (LLMs) advance in their capabilities, researchers have increasingly employed them for social simulation. In this paper, we investigate whether interactions among LLM agents resemble those of humans. Specifically, we focus on the pronoun usage difference between leaders and non-leaders, examining whether the simulation would lead to human-like pronoun usage patterns during the LLMs' interactions. Our evaluation reveals the significant discrepancies between LLM-based simulations and human pronoun usage, with prompt-based or specialized agents failing to demonstrate human-like pronoun usage patterns. In addition, we reveal that even if LLMs understand the human pronoun usage patterns, they fail to demonstrate them in the actual interaction process. Our study highlights the limitations of social simulations based on LLM agents, urging caution in using such social simulation in practitioners' decision-making process.
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。
