As Large Language Model (LLM)-based agents increasingly engage with human society, how well do we understand their prosocial behaviors? We (1) investigate how LLM agents' prosocial behaviors can be induced by different personas and benchmarked against human behaviors; and (2) introduce a social science approach to evaluate LLM agents' decision-making. We explored how different personas and experimental framings affect these AI agents' altruistic behavior in dictator games and compared their behaviors within the same LLM family, across various families, and with human behaviors. The findings reveal that merely assigning a human-like identity to LLMs does not produce human-like behaviors. These findings suggest that LLM agents' reasoning does not consistently exhibit textual markers of human decision-making in dictator games and that their alignment with human behavior varies substantially across model architectures and prompt formulations; even worse, such dependence does not follow a clear pattern. As society increasingly integrates machine intelligence, "Prosocial AI" emerges as a promising and urgent research direction in philanthropic studies.

翻译：随着基于大语言模型（LLM）的智能体日益融入人类社会，我们对其亲社会行为的理解程度如何？本研究（1）探究了不同角色设定如何诱导LLM智能体的亲社会行为，并将其与人类行为进行基准比较；（2）引入社会科学方法评估LLM智能体的决策机制。我们通过独裁者博弈实验，探索了不同角色设定与实验框架对AI智能体利他行为的影响，并在同一LLM家族内部、不同家族之间以及与人类行为进行了对比分析。研究结果表明，仅赋予LLM类人身份并不能产生类人行为。这些发现表明，在独裁者博弈中，LLM智能体的推理过程并未持续表现出人类决策的文本特征标记，且其与人类行为的对齐程度在不同模型架构和提示词设计下存在显著差异；更严重的是，这种依赖性并未呈现清晰规律。随着社会对机器智能的整合日益深入，“亲社会人工智能”正成为慈善研究领域中一个紧迫且具有前景的研究方向。