EmbDivBench：21 种嵌入多样性度量方法系统评测
Measuring Data Diversity with Embeddings: A Taxonomy and Benchmark for Diversity Measures
做数据筛选或测试集设计的朋友可以看看，论文把 21 种多样性度量跑了个遍，结论是大家默认的 MPD 其实不如 Graph Entropy。
一篇 arXiv 论文对 21 种基于嵌入的文本多样性度量方法进行分类，划分出 4 个计算家族。作者发布 EmbDivBench 基准，从 variety、balance、disparity 三个维度在模拟和自然文本数据上评测这些方法。结果显示最常用的 Mean Pairwise Distance 在三个维度上均被多个替代方法超越，Graph Entropy 整体表现最好。论文最后给出度量方法选择的实践建议。
Measuring Data Diversity with Embeddings: A Taxonomy and Benchmark for Diversity Measures
Diversity is a critical property of text corpora, with direct implications for training data curation, test set design, and model generalization. However, its measurement remains fragmented and poorly understood. Existing embedding-based diversity measures vary widely in how they are computed and can yield substantially different diversity scores on the same data, yet no systematic comparison of their empirical behaviour exists. We make two contributions toward addressing this gap. First, we present a taxonomy of 21 embedding-based diversity measures, organizing them into four families based on their underlying computations. Second, we introduce EmbDivBench, a benchmark that evaluates these measures along three conceptually distinct components (variety, balance and disparity) on both simulated and natural text data. Although Mean Pairwise Distance is the most commonly used measure, our experiments show that it is outperformed by several alternatives on the three diversity components, with Graph Entropy being the best choice overall. Lastly, we distil these findings into practical recommendations for diversity measure selection.
