Summary of A Dual-fusion Cognitive Diagnosis Framework For Open Student Learning Environments, by Yuanhao Liu et al.
A Dual-Fusion Cognitive Diagnosis Framework for Open Student Learning Environments
by Yuanhao Liu, Shuo Liu, Yimeng Liu, Jingwen Yang, Hong Qian
First submitted to arxiv on: 19 Oct 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a dual-fusion cognitive diagnosis framework (DFCD) to address the limitations of existing cognitive diagnosis models (CDMs) in open student learning environments. CDMs aim to infer students’ mastery levels based on historical response logs, but current approaches often require retraining when new exercises or knowledge are introduced. DFCD combines textual semantic features and response-relevant features using a dual-fusion module. The framework first refines exercises and knowledge concepts via large language models and then encodes the refined features with text embedding models. For response-related features, DFCD proposes a novel response matrix that incorporates information within response logs. Experimental results across real-world datasets demonstrate the superiority of DFCD in integrating different modalities and its strong adaptability in open student learning environments. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps computers better understand students’ knowledge levels based on their past answers. Right now, this type of computer program usually needs to be retrained whenever new questions or topics are added. The authors propose a new way to combine different types of information from the student’s responses and semantic features (like word meanings) to make these programs more adaptable and accurate. They test their approach on real-world datasets and show that it outperforms existing methods. |
Keywords
» Artificial intelligence » Embedding
