为编程辅导工具设计预部署审计框架，确保教学反馈符合学习者解释需求。
ExplainRoute: A Pre-Deployment Audit Framework for Non-Answer-Giving Programming Tutors
- 基于学习者解释状态动态选择自问式或苏格拉底式引导回复。
- 在1770组数据上验证，自适应路由效果与固定策略相当，但保持100%合同有效性。
- 适合教育AI研发者用于评估辅导系统的信息边界与教学逻辑可靠性。
编程辅导系统应支持学习者自主解释而非直接给答案。本文提出 ExplainRoute，一种面向非答案型编程辅导工具的预部署审计框架。该框架根据代码行与学习者解释，评估其解释状态，并在两种受限回复间选择：费曼式自解释提示或苏格拉底式支架。框架通过可机器检查的合约公开其状态、策略、引用代码片段及泄露风险。不同于仅以流畅度排名的基准，ExplainRoute 审计信息边界、响应极性、失败闭环和学习者解释可见性价值。我们在含1,770对样本的 SelfCode 语料库上离线评估，使用代码组划分，保留443对样本于11个未触碰的保留组中。对比了直接答案、固定开放式自解释、固定苏格拉底支架、自适应路由及无状态自适应消融方案。合同有效性在所有教学条件下均达100%。自适应路由在60.5%的记录中表现等同于固定参考规则，状态宏平均F1为0.238（开放：0.229；苏格拉底：0.246），未显示显著优势。独立语言模型评分显示，自适应回应得分为4.516/5，优于无状态消融（2.819/5），但略低于固定开放（4.598/5）和固定苏格拉底（4.658/5）。盲评40行分层子集确认，可见学习者解释提升信息价值，但自适应路由未超越固定策略。贡献在于提供经验证的审计协议与边界发现，而非学习效果提升证据。
原文摘要 · Abstract (English)
Programming tutors should support learners' own explanations rather than immediately providing model answers. We present ExplainRoute, a pre-deployment audit framework for non-answer-giving programming tutors. Given a code line and a learner explanation, it estimates the explanation state and selects one of two bounded responses: a Feynman-style self-explanation prompt or a Socratic scaffold. The framework exposes its state, strategy, cited code fragment, and leakage risk through a machine-checkable contract. Unlike benchmarks that rank tutors by fluency alone, ExplainRoute audits information boundaries, response polarity, failure closure, and the value of learner-explanation visibility before classroom deployment. We evaluate it offline on the 1,770-pair SelfCode corpus using a code-group split, with 443 pairs reserved in 11 untouched holdout groups. The evaluation compares direct answers, fixed open self-explanation, fixed Socratic scaffolding, adaptive routing, and an adaptive no-state ablation. Contract validity reaches 100% for all pedagogical conditions. Adaptive routing matches the frozen reference rule on 60.5% of records, with state macro-F1 of 0.238 (Open: 0.229; Socratic: 0.246), showing no reliable adaptive advantage. An independent language-model judge scores adaptive responses 4.516/5, outperforming the no-state ablation (2.819/5) but slightly below fixed open self-explanation (4.598/5) and Socratic scaffolding (4.658/5). A blinded rubric evaluation on a stratified 40-row subset confirms that visible learner explanations improve information value while adaptive routing does not outperform fixed strategies. The contribution is a validated audit protocol and a boundary finding, rather than evidence of improved learning, retention, or causal instructional effectiveness.
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。