ToST：用于多路径引导与并行思考的思维树式苏格拉底教学框架
ToST: A Tree-of-Thought Socratic Teaching Framework for Multi-Path Guidance and Parallel Thinking
- Beijing Normal University（北京师范大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出ToST框架，采用多路径范式与并行策略，建立MPSG-Bench基准，可提升LLMs苏格拉底教学的引导成功率，助力学生探索多解决方案路径。
AI中文摘要：
大型语言模型（LLMs）具备强大的问题解决能力，有望成为苏格拉底教学的智能体，通过逐步的启发性提问引导学生。然而，现有方法通常采用“一个问题一个解决方案”的范式，将教学引导限制在单一的线性推理路径中，这种设计限制了教学灵活性，削弱了错误恢复能力，也限制了学生进行并行思考以探索多种有效解决方案的能力。为克服这些问题，我们提出了ToST，即思维树式苏格拉底教学框架，它在“一个问题多个解决方案”的范式下明确支持多路径引导。ToST采用并行播种（Parallel Sowing）这一面向并行思考的提问策略，鼓励学生从不同角度处理问题；还采用多路径自适应引导机制，在备选解决方案轨迹上提供更稳健的非线性指导。同时，为填补系统评估此类非线性教学能力的空白，我们推进多路径苏格拉底引导任务，建立了MPSG-Bench这一综合基准，其包含3.1万条多路径教学对话数据集，以及基于SOLO（可观察学习成果结构）理论的五维评估框架，用于评估并行思考引导能力。实验结果表明，ToST显著提高了引导成功率，同时在自动指标和人工指标下，能让学生更有效地导航和探索多个解决方案路径。
英文摘要：
Large Language Models (LLMs) exhibit strong problem-solving abilities, positioning them as promising agents for Socratic teaching to guide students through step-by-step heuristic questioning. However, existing approaches typically adopt a one-problem-one-solution paradigm, restricting the teaching guidance to a single linear reasoning path. This design limits instructional flexibility, weakens error recovery, and restricts students' ability to engage in parallel thinking to explore multiple valid solutions. To overcome these, we propose ToST, a Tree-of-Thought Socratic Teaching framework that explicitly supports multi-path guidance under a one-problem-multiple-solutions paradigm. ToST employs Parallel Sowing, a parallel-thinking-oriented questioning strategy to encourage students to approach problems from diverse perspectives, and a Multi-Path Adaptive Guidance mechanism to provide more robust and non-linear instructions across alternative solution trajectories. Concurrently, to fill the void in systematically evaluating such non-linear instructional capabilities, we advance the task of multi-path Socratic guidance by establishing MPSG-Bench, a comprehensive benchmark that includes a dataset of 31K multi-path teaching dialogues and a five-dimensional evaluation framework grounded in the SOLO (Structure of Observed Learning Outcomes) theory to assess parallel-thinking guidance. Experimental results demonstrate that ToST significantly enhances guidance success rates while empowering students to navigate and explore multiple solution paths more effectively under both automatic and human metrics.
