用因果图引导的思维链生成精准教学问题，减少大模型幻觉。
Automatic Question Generation for Intuitive Learning Utilizing Causal Graph Guided Chain of Thought Reasoning
- 用因果图和思维链构建分步推理路径，确保逻辑连贯。
- 相比基线方法，问题质量提升70%，主观评价表现优异。
- 适合需要高质量自动生成习题的智能教育系统使用。
直观学习对发展科学、技术、工程和数学（STEM）教育中的深层概念理解至关重要，但学生常因概念抽象且相互关联而难以掌握。自动问答生成已成为个性化与自适应学习的有效策略，但大型语言模型（LLMs）的幻觉问题导致生成的问题存在事实错误、歧义或教学不一致。为此，我们提出一种新框架，结合因果图引导的思维链（CoT）推理与多智能体LLM架构。因果图显式表征领域知识，思维链推理实现相关概念的结构化逐步遍历。专用的LLM智能体分别负责路径搜索、推理、验证与输出，均在领域约束下运行。双阶段验证机制（概念与输出层面）显著降低幻觉。实验表明，问题质量相较参考方法最高提升70%，主观评估结果也极为理想。
原文摘要 · Abstract (English)
Intuitive learning is crucial for developing deep conceptual understanding, especially in STEM education, where students often struggle with abstract and interconnected concepts. Automatic question generation has become an effective strategy for personalized and adaptive learning. However, its effectiveness is hindered by hallucinations in large language models (LLMs), which may generate factually incorrect, ambiguous, or pedagogically inconsistent questions. To address this issue, we propose a novel framework that combines causal-graph-guided Chain-of-Thought (CoT) reasoning with a multi-agent LLM architecture. This approach ensures the generation of accurate, meaningful, and curriculum-aligned questions. Causal graphs provide an explicit representation of domain knowledge, while CoT reasoning facilitates a structured, step-by-step traversal of related concepts. Dedicated LLM agents are assigned specific tasks such as graph pathfinding, reasoning, validation, and output, all working within domain constraints. A dual validation mechanism-at both the conceptual and output stages-greatly reduces hallucinations. Experimental results demonstrate up to a 70% improvement in quality compared to reference methods and yielded highly favorable outcomes in subjective evaluations.
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。