Large language models assume people are more rational than we really are

R Liu, J Geng, JC Peterson, I Sucholutsky… - arXiv preprint arXiv …, 2024 - arxiv.org
In order for AI systems to communicate effectively with people, they must understand how we
make decisions. However, people's decisions are not always rational, so the implicit internal …

Beyond demographics: aligning role-playing LLM-based agents using human belief networks

YS Chuang, K Nirunwiroj, Z Studdiford, A Goyal… - arXiv preprint arXiv …, 2024 - arxiv.org
Creating human-like large language model (LLM) agents is crucial for faithful social
simulation. Having LLMs role-play based on demographic information sometimes improves …

Evaluating cultural adaptability of a large language model via simulation of synthetic personas

L Kwok, M Bravansky, LD Griffin - arXiv preprint arXiv:2408.06929, 2024 - arxiv.org
The success of Large Language Models (LLMs) in multicultural environments hinges on
their ability to understand users' diverse cultural backgrounds. We measure this capability by …

A Comprehensive Survey of Large Language Models in Management: Applications, Challenges, and Opportunities

H Zhao, L Wu, Y Shan, Z Jin, Y Sui, Z Liu… - … (August 14, 2024), 2024 - papers.ssrn.com
This survey examines the transformative impact of Large Language Models (LLMs) and AI-
driven systems across three critical and interconnected business domains: Finance …

Intelligent Computing Social Modeling and Methodological Innovations in Political Science in the Era of Large Language Models

Z Wang, Y Xu, D Wang, L Zhou, Y Zhou - arXiv preprint arXiv:2410.16301, 2024 - arxiv.org
The recent wave of artificial intelligence, epitomized by large language models (LLMs), has
presented opportunities and challenges for methodological innovation in political science …

Artificial data, real insights: Evaluating opportunities and risks of expanding the data ecosystem with synthetic data

R Timpone, Y Yang - arXiv preprint arXiv:2408.15260, 2024 - arxiv.org
Synthetic Data is not new, but recent advances in Generative AI have raised interest in
expanding the research toolbox, creating new opportunities and risks. This article provides a …

Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study

B Ma, B Yoztyurk, AC Haensch, X Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
In recent research, large language models (LLMs) have been increasingly used to
investigate public opinions. This study investigates the algorithmic fidelity of LLMs, ie, the …

The creative psychometric item generator: a framework for item generation and validation using large language models

A Laverghetta Jr, S Luchini, A Linell… - arXiv preprint arXiv …, 2024 - arxiv.org
Increasingly, large language models (LLMs) are being used to automate workplace
processes requiring a high degree of creativity. While much prior work has examined the …

AI and Epistemic Risk for Democracy: A Coming Crisis of Public Knowledge?

J Wihbey - Available at SSRN, 2024 - papers.ssrn.com
As advanced artificial intelligence (AI) technologies are developed and deployed, core
zones of information and knowledge that support democratic life will be mediated more …

Kiss up, Kick down: Exploring Behavioral Changes in Multi-modal Large Language Models with Assigned Visual Personas

S Sun, E Lee, SY Baek, S Hwang, W Lee… - arXiv preprint arXiv …, 2024 - arxiv.org
This study is the first to explore whether multi-modal large language models (LLMs) can
align their behaviors with visual personas, addressing a significant gap in the literature that …