不用训练的统一学习诊断框架，小模型也能精准预测与推荐
A Training-Free Large Reasoning Model-based Knowledge Tracing Framework for Unified Prediction and Prescription
- 用测试时扩展技术让小模型实现强推理能力
- 单次输出完成预测、反馈和推荐，准确率媲美大模型
- 揭示小模型推理轨迹，为智能教学系统提供新思路
知识追踪（KT）旨在根据学习者交互历史估计其掌握程度。近期研究尝试用大语言模型（LLM）进行KT，但通常需要微调，且性能不稳定或接近随机。此外，以往系统多仅关注预测，依赖多阶段流水线生成反馈与推荐，导致系统复杂且资源消耗高。为此，我们提出Thinking-KT——一种无需训练的KT框架，引入测试时扩展（TTS），使小型LLM也能达到竞争力的KT表现。在此框架中，小型LLM可联合完成预测、个性化反馈生成与学习建议，在不降低预测精度的前提下实现一体化输出。我们还系统分析了KT中的推理轨迹，结果表明TTS是大模型驱动KT中关键但被忽视的因素，小型LLM可作为统一智能导师引擎。
原文摘要 · Abstract (English)
Knowledge Tracing (KT) aims to estimate a learner's evolving mastery based on interaction histories. Recent studies have explored Large Language Models (LLMs) for KT via autoregressive nature, but such approaches typically require fine-tuning and exhibit unstable or near-random performance. Moreover, prior KT systems primarily focus on prediction and rely on multi-stage pipelines for feedback and recommendation, resulting in increased system complexity and resources. To address this gap, we propose Thinking-KT, a training-free KT framework that incorporates Test-Time Scaling (TTS), enabling even small LLMs to achieve competitive KT performance. Moreover, in this framework, a small LLM can jointly perform KT prediction, personalized feedback generation, and learning recommendation in a unified output without degrading prediction accuracy. Beyond performance, we present the systematic analysis of reasoning traces in KT. Our results demonstrate that TTS is a critical yet underexplored factor in LLM-based KT, and that small LLMs can serve as unified ITS engines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。