面向稠密与稀疏检索器的运行建议：HNSW、Flat 还是倒排索引？
Operational Advice for Dense and Sparse Retrievers: HNSW, Flat, or Inverted Indexes?
AI总结：
本文基于 Lucene 在 BEIR 上比较 HNSW、flat（含量化变体）与稀疏倒排索引，从索引时间、查询性能和检索质量给出稠密与稀疏检索器的选型建议。
摘要：
如今从事稠密检索的从业者面临着令人眼花缭乱的众多选择。除选择嵌入模型外，另一个影响重大的选择是近邻向量搜索的具体实现。尽管最佳实践推荐使用 HNSW 索引，但采用暴力搜索的 flat 向量索引代表了另一种可行方案，尤其适用于较小语料库和快速原型开发。本文中，我们利用开源 Lucene 搜索库在 BEIR 数据集上给出实验结果，从索引时间、查询评估性能和检索质量的角度阐明 HNSW 与 flat 索引（包括量化变体）之间的权衡。通过对稠密与稀疏检索器的额外比较，我们的结果为当今的搜索从业者理解稠密和稀疏检索器的设计空间提供了指导。据我们所知，我们是首个在此方面提供由实证实验支持的运行建议的研究。
英文摘要：
Practitioners working on dense retrieval today face a bewildering number of choices. Beyond selecting the embedding model, another consequential choice is the actual implementation of nearest-neighbor vector search. While best practices recommend HNSW indexes, flat vector indexes with brute-force search represent another viable option, particularly for smaller corpora and for rapid prototyping. In this paper, we provide experimental results on the BEIR dataset using the open-source Lucene search library that explicate the tradeoffs between HNSW and flat indexes (including quantized variants) from the perspectives of indexing time, query evaluation performance, and retrieval quality. With additional comparisons between dense and sparse retrievers, our results provide guidance for today's search practitioner in understanding the design space of dense and sparse retrievers. To our knowledge, we are the first to provide operational advice supported by empirical experiments in this regard.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
