An LLM-based Delphi Study to Predict GenAI Evolution

TL;DR

This paper presents a novel method using Large Language Models to conduct Delphi studies for forecasting the future of Generative AI, capturing diverse perspectives and structured scenarios despite some limitations.

Contribution

It introduces a new LLM-based Delphi methodology for qualitative forecasting of complex, evolving systems like Generative AI.

Findings

LLM-based Delphi can facilitate structured scenario analysis.

The approach captures diverse perspectives and mitigates respondent fatigue.

Limitations include knowledge cutoffs and inherent biases.

Abstract

Predicting the future trajectory of complex and rapidly evolving systems remains a significant challenge, particularly in domains where data is scarce or unreliable. This study introduces a novel approach to qualitative forecasting by leveraging Large Language Models to conduct Delphi studies. The methodology was applied to explore the future evolution of Generative Artificial Intelligence, revealing insights into key factors such as geopolitical tensions, economic disparities, regulatory frameworks, and ethical considerations. The results highlight how LLM-based Delphi studies can facilitate structured scenario analysis, capturing diverse perspectives while mitigating issues such as respondent fatigue. However, limitations emerge in terms of knowledge cutoffs, inherent biases, and sensitivity to initial conditions. While the approach provides an innovative means for structured foresight, this method could be also considered as a novel form of reasoning. further research is needed to refine its ability to manage heterogeneity, improve reliability, and integrate external data sources.