Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.21239 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918036511916032 |
|---|---|
| author | He, Yu Yao, Zihan Song, Chentao Qi, Tianyu Liu, Jun Li, Ming Huang, Qing |
| author_facet | He, Yu Yao, Zihan Song, Chentao Qi, Tianyu Liu, Jun Li, Ming Huang, Qing |
| contents | Cognitive Diagnosis (CD) has become a critical task in AI-empowered education, supporting personalized learning by accurately assessing students' cognitive states. However, traditional CD models often struggle in cold-start scenarios due to the lack of student-exercise interaction data. Recent NLP-based approaches leveraging pre-trained language models (PLMs) have shown promise by utilizing textual features but fail to fully bridge the gap between semantic understanding and cognitive profiling. In this work, we propose Language Models as Zeroshot Cognitive Diagnosis Learners (LMCD), a novel framework designed to handle cold-start challenges by harnessing large language models (LLMs). LMCD operates via two primary phases: (1) Knowledge Diffusion, where LLMs generate enriched contents of exercises and knowledge concepts (KCs), establishing stronger semantic links; and (2) Semantic-Cognitive Fusion, where LLMs employ causal attention mechanisms to integrate textual information and student cognitive states, creating comprehensive profiles for both students and exercises. These representations are efficiently trained with off-the-shelf CD models. Experiments on two real-world datasets demonstrate that LMCD significantly outperforms state-of-the-art methods in both exercise-cold and domain-cold settings. The code is publicly available at https://github.com/TAL-auroraX/LMCD |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_21239 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LMCD: Language Models are Zeroshot Cognitive Diagnosis Learners He, Yu Yao, Zihan Song, Chentao Qi, Tianyu Liu, Jun Li, Ming Huang, Qing Computation and Language Cognitive Diagnosis (CD) has become a critical task in AI-empowered education, supporting personalized learning by accurately assessing students' cognitive states. However, traditional CD models often struggle in cold-start scenarios due to the lack of student-exercise interaction data. Recent NLP-based approaches leveraging pre-trained language models (PLMs) have shown promise by utilizing textual features but fail to fully bridge the gap between semantic understanding and cognitive profiling. In this work, we propose Language Models as Zeroshot Cognitive Diagnosis Learners (LMCD), a novel framework designed to handle cold-start challenges by harnessing large language models (LLMs). LMCD operates via two primary phases: (1) Knowledge Diffusion, where LLMs generate enriched contents of exercises and knowledge concepts (KCs), establishing stronger semantic links; and (2) Semantic-Cognitive Fusion, where LLMs employ causal attention mechanisms to integrate textual information and student cognitive states, creating comprehensive profiles for both students and exercises. These representations are efficiently trained with off-the-shelf CD models. Experiments on two real-world datasets demonstrate that LMCD significantly outperforms state-of-the-art methods in both exercise-cold and domain-cold settings. The code is publicly available at https://github.com/TAL-auroraX/LMCD |
| title | LMCD: Language Models are Zeroshot Cognitive Diagnosis Learners |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.21239 |