Exploring the Cognitive Knowledge Structure of Large Language Models: An Educational Diagnostic Assessment Approach

TL;DR

This paper investigates the cognitive knowledge structure of Large Language Models using an educational diagnostic assessment approach, revealing their knowledge patterns and cognitive capabilities to inform future development.

Contribution

It introduces a novel evaluation method based on Bloom's Taxonomy to analyze LLMs' knowledge structures, filling a gap in cognitive research on these models.

Findings

Revealed diverse cognitive patterns of LLMs

Provided insights into models' knowledge organization

Highlighted implications for LLM development

Abstract

Large Language Models (LLMs) have not only exhibited exceptional performance across various tasks, but also demonstrated sparks of intelligence. Recent studies have focused on assessing their capabilities on human exams and revealed their impressive competence in different domains. However, cognitive research on the overall knowledge structure of LLMs is still lacking. In this paper, based on educational diagnostic assessment method, we conduct an evaluation using MoocRadar, a meticulously annotated human test dataset based on Bloom Taxonomy. We aim to reveal the knowledge structures of LLMs and gain insights of their cognitive capabilities. This research emphasizes the significance of investigating LLMs' knowledge and understanding the disparate cognitive patterns of LLMs. By shedding light on models' knowledge, researchers can advance development and utilization of LLMs in a more informed and effective manner.