Why Did Apple Fall: Evaluating Curiosity in Large Language Models

TL;DR

This paper evaluates the curiosity of large language models using a comprehensive framework inspired by human curiosity scales, revealing their strong knowledge-seeking tendencies and potential for enhanced reasoning.

Contribution

It introduces a novel evaluation framework for curiosity in LLMs based on human assessment scales, linking curiosity with improved reasoning and active learning.

Findings

LLMs show a stronger thirst for knowledge than humans.

LLMs tend to make conservative choices in uncertain situations.

Curiosity behaviors can enhance LLM reasoning and active learning.

Abstract

Curiosity serves as a pivotal conduit for human beings to discover and learn new knowledge. Recent advancements of large language models (LLMs) in natural language processing have sparked discussions regarding whether these models possess capability of curiosity-driven learning akin to humans. In this paper, starting from the human curiosity assessment questionnaire Five-Dimensional Curiosity scale Revised (5DCR), we design a comprehensive evaluation framework that covers dimensions such as Information Seeking, Thrill Seeking, and Social Curiosity to assess the extent of curiosity exhibited by LLMs. The results demonstrate that LLMs exhibit a stronger thirst for knowledge than humans but still tend to make conservative choices when faced with uncertain environments. We further investigated the relationship between curiosity and thinking of LLMs, confirming that curious behaviors can enhance the model's reasoning and active learning abilities. These findings suggest that LLMs have the potential to exhibit curiosity similar to that of humans, providing experimental support for the future development of learning capabilities and innovative research in LLMs.