用AI批量评分物理手写试卷，结果与人工评分高度一致。
Large Scale AI Grading of Handwritten Physics Assessments: Score Agreement and Olympiad Team Selection Outcomes
- 基于GPT-5.5的AI双轮评分，用官方评分标准逐页打分。
- 总分相关性达0.91–0.97，最终选拔团队与人工评分完全一致。
- 适合高风险考试的辅助评审，尤其需详细评分细则支持。
多模态AI可读取手写物理解答，但高阶评分需与官方分数和选拔结果保持一致。本研究评估了基于GPT-5.5的评分系统在三类考试中的表现：全国物理奥赛理论题、奥赛选拔营（含理论与实验）及大学量子力学考试。共处理520份手写答卷，总计10364页扫描件，由416名不同考生提交。每份答卷由AI两次评分，第二轮使用根据首轮分歧分析优化的逐页与证据定位指令。评分时AI未见人工评分或对比数据。总分与官方评分的相关性为0.91–0.97。在最终奥赛选拔中，AI选出的五人队伍与人工评分完全一致。第二轮提升了整体题部分的评分一致性，尤其在首轮分歧较大的部分。主要挑战仍在于实验题的精确部分得分判定。因此，可靠AI评分依赖详尽评分标准，应作为受监考员控制的第二评审或审计工具。
原文摘要 · Abstract (English)
Multimodal AI can read handwritten physics solutions, but high-stakes grading requires agreement with official scores and outcomes. This study evaluated GPT-5.5-based grading on 10364 scanned pages from 520 handwritten submissions by 416 unique candidates or students across three assessments: a national Physics Olympiad theory examination, the final Olympiad selection camp with theory and experiment components, and a university quantum-mechanics examination. Each submission was graded twice by AI using the official rubrics. The second round used revised page-by-page and evidence-location instructions developed after first-round disagreement analysis. During grading, AI did not see official human marks or AI--human comparisons. Total-score correlations with official marks were high (0.91--0.97). For the final Olympiad selection, AI recovered the same five-student team as official grading. The second round improved aggregate question-part agreement, especially where first-round disagreements were larger. The main difficulty remained exact partial-credit grading, especially in experimental work. Reliable AI grading therefore depends on detailed rubrics and should be used as a second reader or audit tool under examiner control.
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。