两篇新研究论文探讨了改进信息检索系统的方法。第一篇论文《稀疏检索机制下的静态剪枝》研究了静态剪枝技术如何在不同检索引擎中应用，发现索引端剪枝能持续降低延迟和索引大小，而查询剪枝常被现代系统内化。第二篇论文《Dense Expands, Sparse Anchors》介绍了DESA，一种通道非对称查询扩展方法，它使用LLM生成互补的段落，提高了检索效果并降低了混合检索系统的访问深度。 AI
影响 这些论文在检索效率和效果方面提供了进步，可能影响搜索引擎性能和LLM集成。
排序理由 两篇在arXiv上发表的独立研究论文，详细介绍了信息检索的新方法。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2608.16309v1 Announce Type: cross Abstract: Static pruning is widely used to accelerate sparse neural retrieval, yet existing studies each validate their conclusions within a single custom pipeline, leaving it unclear which findings transfer to modern engines with different…
arXiv:2608.15851v1 Announce Type: cross Abstract: LLM-based query expansion improves retrieval by generating document-like passages. In hybrid retrieval, however, most evaluations fuse fixed top-$L$ dense and sparse rankings. Because the cutoff controls both which cross-channel c…
Static pruning is widely used to accelerate sparse neural retrieval, yet existing studies each validate their conclusions within a single custom pipeline, leaving it unclear which findings transfer to modern engines with different index organizations and dynamic pruning mechanism…
LLM-based query expansion improves retrieval by generating document-like passages. In hybrid retrieval, however, most evaluations fuse fixed top-$L$ dense and sparse rankings. Because the cutoff controls both which cross-channel contributions enter fusion and how much of each ran…