通过几何稳定性与邻域密度评估嵌入质量，提升检索系统查询级性能。
Semantic Certainty Assessment in Vector Retrieval Systems: A Novel Framework for Embedding Quality Evaluation
- 结合量化鲁棒性与邻域密度，判断嵌入质量。
- 在4个标准数据集上召回率提升9.4±1.2%。
- 轻量高效，适合需要自适应检索的场景。
向量检索系统因嵌入质量差异导致查询间性能波动显著。本文提出一种轻量级框架，通过融合量化鲁棒性与邻域密度指标，在查询级别预测检索性能。方法基于高质量嵌入在嵌入空间中占据几何稳定区域且邻域结构一致的观察。在4个标准检索数据集上评估，相较竞争基线在Recall@10上实现9.4±1.2%的持续提升。该框架计算开销极低（低于检索时间的5%），支持自适应检索策略。分析揭示了不同查询类型下嵌入质量的系统性模式，为针对性训练数据增强提供指导。
原文摘要 · Abstract (English)
Vector retrieval systems exhibit significant performance variance across queries due to heterogeneous embedding quality. We propose a lightweight framework for predicting retrieval performance at the query level by combining quantization robustness and neighborhood density metrics. Our approach is motivated by the observation that high-quality embeddings occupy geometrically stable regions in the embedding space and exhibit consistent neighborhood structures. We evaluate our method on 4 standard retrieval datasets, showing consistent improvements of 9.4$\pm$1.2\% in Recall@10 over competitive baselines. The framework requires minimal computational overhead (less than 5\% of retrieval time) and enables adaptive retrieval strategies. Our analysis reveals systematic patterns in embedding quality across different query types, providing insights for targeted training data augmentation.
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。