LLMs 已经是好导师:面向教学数学辅导的无训练提示优化
LLMs Are Already Good Tutors: Training-Free Prompt Optimization for Pedagogical Math Tutoring
AI总结:
本研究探索通过API调用优化系统提示的无训练方法,提出5种教育专用方法,在2个OOD基准上评估12种方法,发现所有方法均超越最强RL训练基线,ParetoGrad在事后解决率、泄漏控制和有用性上达到最佳帕累托平衡。
摘要:
将LLMs与数学辅导对齐通常需要基于RL的训练和多GPU基础设施。我们研究无训练提示优化——仅通过API调用演化系统提示——是否可以作为实用替代方案。我们改编了7种已发表方法并提出了5种教育专用方法,在2个OOD基准套件上的5种条件下评估这12种方法。所有12种最佳方法配置均超越了最强的RL训练基线(R_total = 0.633),我们的ParetoGrad在事后解决率、泄漏控制和有用性上实现了最佳帕累托平衡,而非在任何单一组件上占优。使用包含82个代码的教育代码本进行行为分析发现,无训练方法依赖教学知识模式的频率是RL训练模型的2-3倍,同时意图级脚手架减少了约10个百分点。我们还发现一个任务依赖的推理模式效应,在无训练和基于RL的范式中一致。我们的方法仅通过提示和最小计算即可高效开发教学对齐的LLM导师。
英文摘要:
Aligning LLMs for math tutoring typically requires RL-based training with multi-GPU infrastructure. We investigate whether training-free prompt optimization-evolving only the system prompt via API calls-can serve as a practical alternative. We adapt 7 published methods and propose 5 education-specialized methods, evaluating these 12 methods under 5 conditions on 2 OOD benchmark suites. All 12 best-per-method configurations surpass the strongest RL-trained baseline (R_total = 0.633), and our ParetoGrad achieves the best Pareto balance across post-test solve rate, leak control, and helpfulness, rather than dominating any single component. Behavioral analysis with an 82-code educational codebook reveals that training-free methods rely on teaching-knowledge patterns at 2-3x the rate of RL-trained models, with a compensating ~10 percentage-point reduction in intent-level scaffolding. We also find a task-dependent reasoning mode effect consistent across training-free and RL-based paradigms. Our approach enables efficient development of pedagogically aligned LLM tutors with prompts alone and minimal compute.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。