arXiv 2603.222892026-03-03cs.CLcs.AI

MERIT: 用于可解释知识追踪的记忆增强检索

MERIT: Memory-Enhanced Retrieval for Interpretable Knowledge Tracing

School of Computer Science and Technology, East China Normal University（东华师范大学计算机科学与技术学院）；Shanghai Innovation Institute（上海创新研究院）；WeChat AI, Tencent（微信AI，腾讯）

Runze Li, Kedi Chen, Guwei Feng, Mo Yu, Jun Wang, Wei Zhang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

MERIT提出一种无需训练的框架，结合冻结LLM推理与结构化教学记忆，通过语义去噪将学生分类为潜在认知模式，并构建模式库生成显式推理依据，提升教育诊断的可解释性和效率。

摘要：

知识追踪（KT）模型通过跟踪学生知识状态预测未来表现，是个性化教育的基础。传统深度学习模型虽准确度高，但缺乏可解释性；大语言模型（LLM）具备强推理能力，但存在上下文窗口小和幻觉问题。现有基于LLM的方法通常需要昂贵的微调，限制了扩展性和对新数据的适应性。本文提出MERIT（Memory-Enhanced Retrieval for Interpretable Knowledge Tracing），一种无需训练的框架，结合冻结LLM推理与结构化教学记忆。该框架不更新参数，而是将原始交互日志转换为可解释的记忆库。框架利用语义去噪将学生分类为潜在认知模式，并构建模式库，通过离线分析代表性错误模式生成显式Chain-of-Thought（CoT）推理依据。在推理阶段，分层路由机制检索相关上下文，逻辑增强模块应用语义约束校准预测。通过将LLM扎根于可解释的记忆中，MERIT在真实世界数据集上实现最先进的性能，无需梯度更新。此方法降低计算成本，支持动态知识更新，提升教育诊断的可访问性和透明度。

英文摘要：

Knowledge Tracing (KT) models students' evolving knowledge states to predict future performance, serving as a foundation for personalized education. While traditional deep learning models achieve high accuracy, they often lack interpretability. Large Language Models (LLMs) offer strong reasoning capabilities but struggle with limited context windows and hallucinations. Furthermore, existing LLM-based methods typically require expensive fine-tuning, limiting scalability and adaptability to new data. We propose MERIT (Memory-Enhanced Retrieval for Interpretable Knowledge Tracing), a training-free framework combining frozen LLM reasoning with structured pedagogical memory. Rather than updating parameters, MERIT transforms raw interaction logs into an interpretable memory bank. The framework uses semantic denoising to categorize students into latent cognitive schemas and constructs a paradigm bank where representative error patterns are analyzed offline to generate explicit Chain-of-Thought (CoT) rationales. During inference, a hierarchical routing mechanism retrieves relevant contexts, while a logic-augmented module applies semantic constraints to calibrate predictions. By grounding the LLM in interpretable memory, MERIT achieves state-of-the-art performance on real-world datasets without gradient updates. This approach reduces computational costs and supports dynamic knowledge updates, improving the accessibility and transparency of educational diagnosis.

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。