Skip to content

Opening book details…

About this document

Cikm 2024 by present1136 is a document available to read on EtoBox.

This paper presents an attribute-aware approach to mitigate cold-start problems in Knowledge Tracing (KT) using Large Language Models (LLMs). The proposed Exercise Attribute-aware Knowledge Tracing model (EAKT) estimates question attributes like difficulty and response time, enhancing question representation and addressing sparsity issues. Experimental results demonstrate that EAKT outperforms existing state-of-the-art models while providing improved interpretability in knowledge state transitions.

Author
present1136
Language
EN