Hypothesis Generation with Large Language Models

TL;DR

This paper explores how large language models can generate and refine hypotheses from data, leading to improved predictive accuracy and new scientific insights, surpassing traditional methods.

Contribution

It introduces an iterative hypothesis generation method using LLMs with a reward-based update, enhancing predictive performance and uncovering novel insights.

Findings

Improved accuracy by 31.7% on synthetic data

Enhanced real-world dataset performance by up to 24.9%

Generated hypotheses corroborate and extend human theories

Abstract

Effective generation of novel hypotheses is instrumental to scientific progress. So far, researchers have been the main powerhouse behind hypothesis generation by painstaking data analysis and thinking (also known as the Eureka moment). In this paper, we examine the potential of large language models (LLMs) to generate hypotheses. We focus on hypothesis generation based on data (i.e., labeled examples). To enable LLMs to handle arbitrarily long contexts, we generate initial hypotheses from a small number of examples and then update them iteratively to improve the quality of hypotheses. Inspired by multi-armed bandits, we design a reward function to inform the exploitation-exploration tradeoff in the update process. Our algorithm is able to generate hypotheses that enable much better predictive performance than few-shot prompting in classification tasks, improving accuracy by 31.7% on a synthetic dataset and by 13.9%, 3.3% and, 24.9% on three real-world datasets. We also outperform supervised learning by 12.8% and 11.2% on two challenging real-world datasets. Furthermore, we find that the generated hypotheses not only corroborate human-verified theories but also uncover new insights for the tasks.