arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.01708cs.CL
收藏

基于大推理模型的无训练知识追踪框架:用于统一预测与处方

A Training-Free Large Reasoning Model-based Knowledge Tracing Framework for Unified Prediction and Prescription

Chosun University(全州大学);Neudive Inc(Neudive公司);Independent Researcher(独立研究者)

Unggi Lee, Joo Young Kim, Ran Ju, Minyoung Jung, Jeyeon Eo

AI总结:

本文提出Thinking-KT框架,利用测试时缩放技术,使小型LLM在无需训练的情况下实现高效的知识追踪预测、个性化反馈和学习推荐。

摘要:

知识追踪(KT)旨在根据交互历史估计学习者的逐步掌握情况。近期研究探索了通过自回归性质利用大语言模型(LLMs)进行KT,但此类方法通常需要微调,并表现出不稳定或接近随机的性能。此外,先前的KT系统主要集中在预测上,依赖多阶段流程进行反馈和推荐,导致系统复杂性和资源消耗增加。为解决这一差距,我们提出了Thinking-KT,一种无训练的KT框架,结合了测试时缩放(TTS),使小型LLMs也能实现具有竞争力的KT性能。此外,在该框架中,小型LLMs可以在统一输出中联合执行KT预测、个性化反馈生成和学习推荐,而不降低预测准确性。除了性能外,我们还系统分析了KT中的推理痕迹。我们的结果表明,TTS是LLM-based KT中的关键但被忽视的因素,且小型LLMs可以作为统一的智能教学系统(ITS)引擎。

英文摘要:

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.

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。

↑