LLMs Tackle Meta-Analysis: Automating Scientific Hypothesis Generation with Statistical Rigor

Tung-Wei Lin, Runing Yang, Zain ul Abdeen, Alberto Sangiovanni-Vincentelli, Haibo Huang, Ming Jin

Keywords: Meta-Analysis, Large Language Models, Hypothesis Generation

TL;DR: Large Language Models for automating meta-analysis and generating hypotheses based on extracted information.

Abstract: We propose the use of Large Language Models (LLMs) for generating statistically supported hypotheses from scientific literature. We present a two-stage framework that effectively leverages LLMs' capacity to analyze vast literature and extract pertinent information to formulate evidence-based hypotheses. Our method comprises two phases: 1) data extraction via decomposed zero-shot prompting, and 2) hypothesis generation by auto-formulating and solving an optimization problem. We demonstrate this framework in agricultural science, where field data is particularly limited.

Archival Option: The authors of this submission want it to appear in the archival proceedings.

Submission Number: 16