发现并纠正学生答对题却用错方法的隐藏错误，避免误导性反馈。
The Correct Answer Trap: Pedagogically-Grounded Detection and Feedback for Hidden Misconceptions
- 用评分标准区分答案对错与解法合理性，识别隐藏错误
- 检测准确率达84%，但误报率高，需进一步验证
- 适合教育系统开发者和教师，提升个性化反馈质量
依赖答案正确性的自动反馈系统，在学生通过错误推理得出正确答案时，反而会强化其误解。我们基于Eedi数学平台的20,964条真实学生作答数据，研究了隐藏误解的自动检测问题。微调分类器仅能检测57%的此类错误，标准机器学习干预未能提升效果。开放权重的推理模型可检测84%，但在实际发生率下，误报数量约为真实检测的8倍。为此，我们提出一种分层评估量规，将答案正确性与解法有效性分离，并设计‘检测-验证-升级’流程：对不确定案例，通过诊断性追问而非直接上报教师处理。该系统支持两种部署模式：教师仪表盘用于过滤待审任务队列，自主导师模式则触发低成本形成性跟进。
原文摘要 · Abstract (English)
Automated feedback systems that rely on answer correctness will reinforce, rather than address, misconceptions when students reach the correct answer through flawed reasoning. We investigate automatic detection of these hidden misconceptions using 20,964 real student responses from the Eedi mathematics platform. Fine-tuned classifiers detect only 57% of these hidden misconceptions, and standard ML interventions do not improve on this. An open-weight reasoning model detects 84%, but at realistic prevalence, false alarms outnumber genuine detections roughly 8 to 1. We present a graduated assessment rubric that separates answer correctness from method validity, and propose a detect-verify-escalate pipeline that routes uncertain cases to diagnostic follow-up questions rather than directly to teachers. Two deployment modes adapt the pipeline: a teacher dashboard where the system filters a review queue, and an autonomous tutor where flags trigger low-cost formative follow-up.
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。