用多模态模型量化高校招生的综合评估，提升透明度与公平性。
Quantifying Holistic Review: A Multi-Modal Approach to College Admissions Prediction
- 将申请者资料拆解为学术、文书、课外三部分，分别建模评分
- 文书质量预测R²达0.80，分类准确率超75%，模型表现接近人工评判
- 适合关注招生公平性与可解释性的教育技术研究者
本文提出综合申请人评分系统（CAPS），一种新型多模态框架，用于量化建模和解释高校招生中的整体评估。CAPS将申请者档案分解为三个可解释的组成部分：学术表现（标准化学术分，SAS）、文书质量（文书质量指数，EQI）和课外活动影响力（课外活动影响分，EIS）。通过基于Transformer的语义嵌入、大语言模型评分和XGBoost回归，CAPS提供与人类判断一致的透明且可解释的评估。在合成但真实感强的数据集上进行实验，结果显示文书质量预测的R²为0.80，分类准确率超过75%，宏平均F1得分为0.69，加权F1得分为0.74。该方法解决了传统整体评估中透明度低、标准不一及申请者焦虑等关键问题，为更公平、数据驱动的招生实践铺平道路。
原文摘要 · Abstract (English)
This paper introduces the Comprehensive Applicant Profile Score (CAPS), a novel multi-modal framework designed to quantitatively model and interpret holistic college admissions evaluations. CAPS decomposes applicant profiles into three interpretable components: academic performance (Standardized Academic Score, SAS), essay quality (Essay Quality Index, EQI), and extracurricular engagement (Extracurricular Impact Score, EIS). Leveraging transformer-based semantic embeddings, LLM scoring, and XGBoost regression, CAPS provides transparent and explainable evaluations aligned with human judgment. Experiments on a synthetic but realistic dataset demonstrate strong performance, achieving an EQI prediction R^2 of 0.80, classification accuracy over 75%, a macro F1 score of 0.69, and a weighted F1 score of 0.74. CAPS addresses key limitations in traditional holistic review -- particularly the opacity, inconsistency, and anxiety faced by applicants -- thus paving the way for more equitable and data-informed admissions practices.
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。