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 2408.07237cs.CLcs.CYphysics.soc-ph
收藏

基于大语言模型的人类信念建模语义嵌入空间

A semantic embedding space based on large language models for modelling human beliefs

Center for Complex Networks and Systems Research(复杂网络与系统研究中心);Luddy School of Informatics, Computing, and Engineering(信息学、计算与工程学院);Indiana University(印第安纳大学)

Byunghwee Lee, Rachith Aiyappa, Yong-Yeol Ahn, Haewoon Kwak, Jisun An

AI总结:

本文提出利用微调大语言模型构建信念嵌入空间,通过在线辩论数据建模数千信念间的关联与极化,并证明该空间可预测新信念和估计认知失调。

摘要:

信念构成人类认知与决策的基础,指导着我们的行动和社会联系。一个能够概括信念及其相互关系的模型,对于理解它们如何影响我们的行为至关重要。然而,关于信念相互作用的研究往往局限于与特定议题相关的信念,并且高度依赖问卷调查。我们提出了一种方法,通过利用在线用户辩论数据,并将信念映射到一个使用微调后的大语言模型(LLM)构建的神经嵌入空间中,来研究数千个信念之间微妙的相互作用。该信念空间捕捉了跨社会议题的多样信念之间的相互关联性和极化程度。我们的研究结果表明,该信念空间中的位置能够预测个体的新信念,并根据现有信念与新信念之间的距离来估计认知失调。这项研究展示了LLM如何与人类信念的集体在线记录相结合,从而为理解支配人类信念形成的基本原理提供洞见。

英文摘要:

Beliefs form the foundation of human cognition and decision-making, guiding our actions and social connections. A model encapsulating beliefs and their interrelationships is crucial for understanding their influence on our actions. However, research on belief interplay has often been limited to beliefs related to specific issues and relied heavily on surveys. We propose a method to study the nuanced interplay between thousands of beliefs by leveraging an online user debate data and mapping beliefs onto a neural embedding space constructed using a fine-tuned large language model (LLM). This belief space captures the interconnectedness and polarization of diverse beliefs across social issues. Our findings show that positions within this belief space predict new beliefs of individuals and estimate cognitive dissonance based on the distance between existing and new beliefs. This study demonstrates how LLMs, combined with collective online records of human beliefs, can offer insights into the fundamental principles that govern human belief formation.

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。

↑