用数据本身做基准，判断模型是否说对了话。
Does the Model Say What the Data Says? A Simple Heuristic for Model Data Alignment
- 从数据中提取特征重要性排序作为基准
- 对比模型解释与数据基准的差异
- 适合想验证模型是否靠谱的从业者
本文提出一种简单高效的框架，用于评估机器学习模型是否与其训练数据的结构一致，即模型是否真正反映了数据所表达的信息。不同于仅关注模型行为解释的现有方法，本方法直接基于数据构建基准：借鉴鲁宾潜在结果框架，量化每个特征在二分类任务中区分两类结果的能力，超越传统描述性统计，估计特征对结果的影响。通过将数据导出的特征排序与模型解释进行比较，为实践者提供一种可解释、模型无关的模型-数据对齐评估方式。
原文摘要 · Abstract (English)
In this work, we propose a simple and computationally efficient framework for evaluating whether machine learning models align with the structure of the data they learn from; that is, whether the model says what the data says. Unlike existing interpretability methods that focus exclusively on explaining model behavior, our approach establishes a baseline derived directly from the data itself. Drawing inspiration from Rubin's Potential Outcomes Framework, we quantify how strongly each feature separates the two outcome groups in a binary classification task, moving beyond traditional descriptive statistics to estimate each feature's effect on the outcome. By comparing these data-derived feature rankings with model-based explanations, we provide practitioners with an interpretable and model-agnostic method for assessing model-data alignment.
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。