Knowledge Tracing (KT) monitors students' knowledge states and simulates their responses to question sequences. Existing KT models typically follow a single-step training paradigm, which leads to discrepancies with the multi-step inference process required in real-world simulations, resulting in significant error accumulation. This accumulation of error, coupled with the issue of data sparsity, can substantially degrade the performance of recommendation models in the intelligent tutoring systems. To address these challenges, we propose a novel Adversarial Multi-Step Training Framework for Knowledge Tracing (AdvKT), which, for the first time, focuses on the multi-step KT task. More specifically, AdvKT leverages adversarial learning paradigm involving a generator and a discriminator. The generator mimics high-reward responses, effectively reducing error accumulation across multiple steps, while the discriminator provides feedback to generate synthetic data. Additionally, we design specialized data augmentation techniques to enrich the training data with realistic variations, ensuring that the model generalizes well even in scenarios with sparse data. Experiments conducted on four real-world datasets demonstrate the superiority of AdvKT over existing KT models, showcasing its ability to address both error accumulation and data sparsity issues effectively.

翻译：知识追踪（Knowledge Tracing，KT）旨在监测学生的知识状态并模拟其对问题序列的响应。现有的KT模型通常遵循单步训练范式，这与实际模拟中所需的多步推理过程存在差异，导致显著的误差累积。这种误差累积，加之数据稀疏性问题，会严重降低智能导学系统中推荐模型的性能。为应对这些挑战，我们提出了一种新颖的对抗性多步训练框架用于知识追踪（AdvKT），该框架首次专注于多步KT任务。具体而言，AdvKT利用包含生成器和判别器的对抗学习范式。生成器模拟高奖励响应，有效减少多步中的误差累积，而判别器则提供反馈以生成合成数据。此外，我们设计了专门的数据增强技术，通过真实的变体来丰富训练数据，确保模型即使在数据稀疏的场景下也能良好泛化。在四个真实世界数据集上进行的实验证明了AdvKT相对于现有KT模型的优越性，展示了其有效解决误差累积和数据稀疏性问题的能力。