arXiv 2502.199152025-04-30cs.AI

LLM驱动的融合双通道难度的有效知识追踪

LLM-driven Effective Knowledge Tracing by Integrating Dual-channel Difficulty

Jiahui Cen, Jianghao Lin, Weixuan Zhong, Dong Zhou, Jin Chen, Aimin Yang, Yongmei Zhou

备注：: During a careful review of our base-experiment results, we discovered a possible error in the way some data were recorded. To ensure the integrity and accuracy of our work, we must correct these results and revise the corresponding analysis before making the manuscript publicly available

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对知识追踪冷启动、个性化建模不清和决策不透明问题，提出DDKT框架，融合LLM与RAG评估难度，引入难度平衡感知、掌握比及知识更新机制，AUC提升2%-10%并增强可解释性。

摘要：

知识追踪（Knowledge Tracing, KT）是智能辅导系统中的一项基础技术，用于模拟学生在学习过程中知识状态的变化，追踪个性化的知识掌握情况，并预测其表现。然而，当前的KT模型面临三大主要挑战：（1）遇到新问题时，由于交互记录稀疏，模型面临冷启动问题，难以进行精确建模；（2）传统模型仅利用历史交互记录进行学生个性化建模，无法准确追踪个体的掌握水平，导致个性化建模不清晰；（3）决策过程对教育者是不透明的，使其难以理解模型的判断。为了应对这些挑战，我们提出了一种新颖的双通道难度感知知识追踪（Dual-channel Difficulty-aware Knowledge Tracing, DDKT）框架。该框架利用大型语言模型（LLMs）和检索增强生成（RAG）进行主观难度评估，同时整合难度偏差感知算法和学生掌握度算法以实现精确的难度测量。我们的框架引入了三项关键创新：（1）难度平衡感知序列（Difficulty Balance Perception Sequence, DBPS）——将学生的主观感知与客观难度相结合，通过注意力机制衡量LLM评估难度、数学统计难度与学生主观感知难度之间的差异；（2）难度掌握比（Difficulty Mastery Ratio, DMR）——通过不同的难度区域对学生掌握水平进行精确建模；（3）知识状态更新机制——通过门控网络实现个性化知识获取，并更新学生的知识状态。在两个真实数据集上的实验结果表明，我们的方法始终优于九个基线模型，将AUC指标提升了2%至10%，同时有效解决了冷启动问题并增强了模型的可解释性。

英文摘要：

Knowledge Tracing (KT) is a fundamental technology in intelligent tutoring systems used to simulate changes in students' knowledge state during learning, track personalized knowledge mastery, and predict performance. However, current KT models face three major challenges: (1) When encountering new questions, models face cold-start problems due to sparse interaction records, making precise modeling difficult; (2) Traditional models only use historical interaction records for student personalization modeling, unable to accurately track individual mastery levels, resulting in unclear personalized modeling; (3) The decision-making process is opaque to educators, making it challenging for them to understand model judgments. To address these challenges, we propose a novel Dual-channel Difficulty-aware Knowledge Tracing (DDKT) framework that utilizes Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) for subjective difficulty assessment, while integrating difficulty bias-aware algorithms and student mastery algorithms for precise difficulty measurement. Our framework introduces three key innovations: (1) Difficulty Balance Perception Sequence (DBPS) - students' subjective perceptions combined with objective difficulty, measuring gaps between LLM-assessed difficulty, mathematical-statistical difficulty, and students' subjective perceived difficulty through attention mechanisms; (2) Difficulty Mastery Ratio (DMR) - precise modeling of student mastery levels through different difficulty zones; (3) Knowledge State Update Mechanism - implementing personalized knowledge acquisition through gated networks and updating student knowledge state. Experimental results on two real datasets show our method consistently outperforms nine baseline models, improving AUC metrics by 2% to 10% while effectively addressing cold-start problems and enhancing model interpretability.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。