闭式与合成孪生：从嵌入统计预测近似最近邻召回率

AI 摘要

本文提出从嵌入统计量预测近似最近邻索引召回率的方法，包括闭式矩统计、合成孪生语料库模拟和轻校准孪生技术，预测误差在0.03以内。研究还发现可通过训练调整得分边际来提升所有索引族的召回率，从而避免逐语料库的变换。该方法支持索引选择、纠错定价和生产召回预测，适用于持续变化的语料库。

正文节选

Closed Forms and Synthetic Twins: Predicting Approximate Nearest Neighbor Recall from Embedding Statistics Abstract Embedding models are trained and evaluated as if retrieval were exact; in production they serve behind approximate indexes — HNSW, IVF, product quantization, or the fixed-dimensional encodings (FDEs) of late-interaction models — whose behavior the encoder’s benchmarks never see: one modern encoder recovers just 14% of its exact top-10 through its raw FDE index. Such failures surfac

发布时间：2026-09-02 12:00

抓取时间：2026-09-02 12:15

来源机构：arXiv