Knowledge is Power: Harnessing Large Language Models for Enhanced Cognitive Diagnosis

TL;DR

This paper introduces a novel framework that leverages large language models to improve cognitive diagnosis by addressing prior knowledge limitations and aligning semantic and behavioral spaces.

Contribution

The paper proposes a model-agnostic Knowledge-enhanced Cognitive Diagnosis framework that integrates LLMs with CDMs using contrastive learning and mask-reconstruction techniques.

Findings

Effective diagnosis of students and exercises using LLMs.

Improved performance on real-world datasets.

Enhanced modeling of cognitive states.

Abstract

Cognitive Diagnosis Models (CDMs) are designed to assess students' cognitive states by analyzing their performance across a series of exercises. However, existing CDMs often struggle with diagnosing infrequent students and exercises due to a lack of rich prior knowledge. With the advancement in large language models (LLMs), which possess extensive domain knowledge, their integration into cognitive diagnosis presents a promising opportunity. Despite this potential, integrating LLMs with CDMs poses significant challenges. LLMs are not well-suited for capturing the fine-grained collaborative interactions between students and exercises, and the disparity between the semantic space of LLMs and the behavioral space of CDMs hinders effective integration. To address these issues, we propose a novel Knowledge-enhanced Cognitive Diagnosis (KCD) framework, which is a model-agnostic framework utilizing LLMs to enhance CDMs and compatible with various CDM architectures. The KCD framework operates in two stages: LLM Diagnosis and Cognitive Level Alignment. In the LLM Diagnosis stage, both students and exercises are diagnosed to achieve comprehensive and detailed modeling. In the Cognitive Level Alignment stage, we bridge the gap between the CDMs' behavioral space and the LLMs' semantic space using contrastive learning and mask-reconstruction approaches. Experiments on several real-world datasets demonstrate the effectiveness of our proposed framework.