arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.08579cs.CL
收藏

基于大语言模型的人类模拟尚不可靠

LLM-based Human Simulations Have Not Yet Been Reliable

National University of Singapore(新加坡国立大学);The Hong Kong University of Science and Technology(香港理工大学);University of Chinese Academy of Sciences(中国科学院大学)

Qian Wang, Jiaying Wu, Zichen Jiang, Zhenheng Tang, Bingqiao Luo, Nuo Chen, Wei Chen, Huacan Wang, Bingsheng He

AI总结:

研究指出基于大语言模型(LLM)的人类模拟不可靠,通过系统回顾找出其在多领域模拟中的问题源于LLM局限与设计缺陷,提出强化数据、提升模型能力及稳健设计的解决框架与算法。

摘要:

大语言模型(LLMs)越来越多地用于模拟不同领域的人类行为。然而,基于LLM的当前人类模拟仍不够可靠,其结果与真实人类行为存在显著差异。我们对社会、经济、政策和心理背景下基于LLM的人类模拟进行系统回顾,找出问题根源并提出解决方案框架和结构化算法。

英文摘要:

Large Language Models (LLMs) are increasingly employed for simulating human behaviors across diverse domains. However, our position is that current LLM-based human simulations remain insufficiently reliable, as evidenced by significant discrepancies between their outcomes and authentic human actions. Our investigation begins with a systematic review of LLM-based human simulations in social, economic, policy, and psychological contexts, identifying their common frameworks, recent advances, and persistent limitations. This review reveals that such discrepancies primarily stem from inherent limitations of LLMs and flaws in simulation design, both of which are examined in detail. Building on these insights, we propose a systematic solution framework that emphasizes enriching data foundations, advancing LLM capabilities, and ensuring robust simulation design to enhance reliability. Finally, we introduce a structured algorithm that operationalizes the proposed framework, aiming to guide credible and human-aligned LLM-based simulations. To facilitate further research, we provide a curated list of related literature and resources at https://github.com/Persdre/awesome-llm-human-simulation.

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。

↑