用提示链引导学生思考，避免直接给答案
Designing and Evaluating Chain-of-Hints for Scientific Question Answering
- 设计静态与动态提示链，逐步引导解题
- 41人实验发现用户更偏好动态提示
- 现有评估指标难以捕捉真实学习体验
大语言模型正在改变教育方式，但直接给出答案可能削弱学生的理解力与思辨能力。已有研究显示，提示能有效促进认知参与。本文评估了18个开源LLM在生成提示链方面的能力，通过两种策略：为每道题预先生成的静态提示，以及根据学习者进展动态调整的动态提示。在五个基于教学原理的自动指标下进行评估。使用表现最佳的LLM开展包含41名参与者定量研究，发现不同提示策略引发明显用户偏好差异，并揭示自动评估指标在捕捉实际体验方面的局限性。研究结果为未来辅导系统的设计提供了关键考量，推动更以学习者为中心的教育技术发展。
原文摘要 · Abstract (English)
LLMs are reshaping education, with students increasingly relying on them for learning. Implemented using general-purpose models, these systems are likely to give away the answers, potentially undermining conceptual understanding and critical thinking. Prior work shows that hints can effectively promote cognitive engagement. Building on this insight, we evaluate 18 open-source LLMs on chain-of-hints generation that scaffold users toward the correct answer. We compare two distinct hinting strategies: static hints, pre-generated for each problem, and dynamic hints, adapted to a learners' progress. We evaluate these systems on five pedagogically grounded automatic metrics for hint quality. Using the best performing LLM as the backbone of a quantitative study with 41 participants, we uncover distinct user preferences across hinting strategies, and identify the limitations of automatic evaluation metrics to capture them. Our findings highlight key design considerations for future research on tutoring systems and contribute toward the development of more learner-centered educational technologies.
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。