Language Representation Favored Zero-Shot Cross-Domain Cognitive Diagnosis

TL;DR

This paper introduces LRCD, a zero-shot cross-domain cognitive diagnosis method that uses language representations to generalize mastery inference across different subjects and platforms, reducing the need for domain-specific training.

Contribution

LRCD leverages textual descriptions and language embeddings to enable zero-shot cognitive diagnosis across multiple domains, addressing limitations of traditional ID-based models.

Findings

LRCD achieves strong zero-shot performance on real-world datasets.

LRCD can rival traditional models trained on full domain data.

Insights into subject and source differences are derived from language-based profiles.

Abstract

Cognitive diagnosis aims to infer students' mastery levels based on their historical response logs. However, existing cognitive diagnosis models (CDMs), which rely on ID embeddings, often have to train specific models on specific domains. This limitation may hinder their directly practical application in various target domains, such as different subjects (e.g., Math, English and Physics) or different education platforms (e.g., ASSISTments, Junyi Academy and Khan Academy). To address this issue, this paper proposes the language representation favored zero-shot cross-domain cognitive diagnosis (LRCD). Specifically, LRCD first analyzes the behavior patterns of students, exercises and concepts in different domains, and then describes the profiles of students, exercises and concepts using textual descriptions. Via recent advanced text-embedding modules, these profiles can be transformed to vectors in the unified language space. Moreover, to address the discrepancy between the language space and the cognitive diagnosis space, we propose language-cognitive mappers in LRCD to learn the mapping from the former to the latter. Then, these profiles can be easily and efficiently integrated and trained with existing CDMs. Extensive experiments show that training LRCD on real-world datasets can achieve commendable zero-shot performance across different target domains, and in some cases, it can even achieve competitive performance with some classic CDMs trained on the full response data on target domains. Notably, we surprisingly find that LRCD can also provide interesting insights into the differences between various subjects (such as humanities and sciences) and sources (such as primary and secondary education).