arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.14744cs.CY
收藏

从社会认知视角探索大语言模型智能体的亲社会非理性

Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View

Xuan Liu, Jie Zhang, Haoyang Shang, Song Guo, Chengxu Yang, Quanyan Zhu

AI总结:

本研究结合社会科学实验与理论,提出利用幻觉特性评估增强大语言模型智能体社会智能的CogMir框架,验证了其与人类在不确定下非理性亲社会决策的一致性,为相关研究提供平台。

摘要:

大语言模型(LLM)因训练数据常包含人类偏见而存在幻觉问题,这一点是否会体现在LLM Agents的决策过程中仍有待充分探究。随着LLM Agents被越来越多地应用于复杂社会环境,一个紧迫且自然的问题随之而来:我们能否利用LLM Agents的系统性幻觉来镜像人类认知偏差,从而展现出非理性的社会智能?本文结合实用社会科学实验与理论洞见,探究了当前LLM Agents中的非理性行为。具体而言,我们提出了CogMir——一个开放式多LLM Agents框架(即认知镜像框架),该框架利用幻觉特性,通过认知偏差来评估并增强LLM Agents的社会智能。在CogMir子集上的实验结果表明,LLM Agents与人类在不确定条件下的非理性决策和亲社会决策表现出高度一致性,这印证了LLM Agents作为社会实体的亲社会性,也凸显了幻觉特性的重要意义。此外,CogMir框架展现出作为宝贵研究平台的潜力,可推动更多针对LLM Agents社会智能的研究。

英文摘要:

Large language models (LLMs) have been shown to face hallucination issues due to the data they trained on often containing human bias; whether this is reflected in the decision-making process of LLM Agents remains under-explored. As LLM Agents are increasingly employed in intricate social environments, a pressing and natural question emerges: Can we utilize LLM Agents' systematic hallucinations to mirror human cognitive biases, thus exhibiting irrational social intelligence? In this paper, we probe the irrational behavior among contemporary LLM Agents by melding practical social science experiments with theoretical insights. Specifically, We propose CogMir, an open-ended Multi-LLM Agents framework that utilizes hallucination properties to assess and enhance LLM Agents' social intelligence through cognitive biases. Experimental results on CogMir subsets show that LLM Agents and humans exhibit high consistency in irrational and prosocial decision-making under uncertain conditions, underscoring the prosociality of LLM Agents as social entities and highlighting the significance of hallucination properties. Additionally, the CogMir framework demonstrates its potential as a valuable platform for encouraging more research into the social intelligence of LLM Agents.

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。

↑