用大模型自动生成知识点标签，再通过语义合并去重，提升准确性。
Leveraging Large Language Models for Identifying Knowledge Components
- 用GPT-4o-mini生成646道题的知识点标签
- 语义合并后将标签数从569减至428，误差降低至0.4259
- 适合想自动化构建教育知识点体系的研究者
知识点（KCs）是自适应学习系统的核心，但由领域专家手动识别存在瓶颈。尽管大语言模型（LLMs）为自动化该过程提供了前景，但以往研究仅限于小数据集，且常生成冗余标签。本研究将一种‘模拟教材’的提示策略（使用GPT-4o-mini）扩展到包含646道多项选择题的大规模数据集。初始自动化方法性能劣于专家设计模型（RMSE 0.4285 vs. 0.4206），并生成569个知识点（专家模型仅101个）。为解决冗余问题，提出基于余弦相似度的语义合并方法。当余弦相似度阈值设为0.8时，模型表现最佳：知识点数量降至428个，RMSE提升至0.4259。结果表明，单纯扩大模型生成不可行，但结合语义合并可有效实现知识点自动识别与优化。
原文摘要 · Abstract (English)
Knowledge Components (KCs) are foundational to adaptive learning systems, but their manual identification by domain experts is a significant bottleneck. While Large Language Models (LLMs) offer a promising avenue for automating this process, prior research has been limited to small datasets and has been shown to produce superfluous, redundant KC labels. This study addresses these limitations by first scaling a "simulated textbook" LLM prompting strategy (using GPT-4o-mini) to a larger dataset of 646 multiple-choice questions. We found that this initial automated approach performed significantly worse than an expert-designed KC model (RMSE 0.4285 vs. 0.4206) and generated an excessive number of KCs (569 vs. 101). To address the issue of redundancy, we proposed and evaluated a novel method for merging semantically similar KC labels based on their cosine similarity. This merging strategy significantly improved the model's performance; a model using a cosine similarity threshold of 0.8 achieved the best result, reducing the KC count to 428 and improving the RMSE to 0.4259. This demonstrates that while scaled LLM generation alone is insufficient, combining it with a semantic merging technique offers a viable path toward automating and refining KC identification.
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。