解决教育大模型被诱导直接给答案的问题，让辅导更安全且有效。
SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs
- 用知识掌握图建模教学逻辑，自动识别学习漏洞
- 在9087组问答上测试，对抗攻击下安全提升显著
- 适合教育AI研发者与评测人员参考
大型语言模型（LLMs）已广泛应用于教育场景。我们发现当前教育类LLM存在关键漏洞：学生可通过诱导性提问获取答案而非引导式指导，称为‘教学劫持’。为系统研究该问题，我们基于知识掌握图统一定义了安全、有用和教学性行为，并提出SHAPE基准，包含9,087个学生提问对，用于评估在对抗压力下的辅导表现。我们设计了一种图增强的辅导流程，通过查询推断前置概念，识别掌握缺口，并利用显式门控机制在指导与解题间动态切换。多模型实验表明，在两种教学劫持设置下，该方法显著提升安全性，同时在相同评估协议下保持接近天花板的帮助性。代码与数据已在https://github.com/MAPS-research/SHaPE公开。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have been widely explored in educational scenarios. We identify a critical vulnerability in current educational LLMs, pedagogical jailbreaks, where students use answer-inducing prompts to elicit solutions rather than scaffolded instructions. To enable systematic study, we unify and formalize safe, helpful, and pedagogical behaviors with a knowledge-mastery graph and introduce SHAPE, a benchmark of 9,087 student-question pairs for evaluating tutoring behavior under adversarial pressure. We propose a graph-augmented tutoring pipeline that infers prerequisite concepts from queries, identifies mastery gaps, and routes generation between instructing and problem-solving via explicit gating. Experiments across multiple LLMs show that our method yields significantly improved safety under two pedagogical jailbreak settings, while maintaining near-ceiling helpfulness under the same evaluation protocol. Our code and data are available at https://github.com/MAPS-research/SHaPE
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。