HRR通过分层重排序，让大模型精准获取长短结合的上下文。
Hierarchical Re-ranker Retriever (HRR)
- 文档按句和512词元分块，兼顾短长查询检索质量。
- 用重排序器在512词元块上打分，避免上下文过粗或过细。
- 最优中间块合并为2048词元父块，供大模型使用。
为解决信息检索中上下文粒度难以平衡的问题——过大导致语义稀释，过小则缺乏背景——本文提出分层重排序检索器（HRR）。HRR将文档切分为句级与512词元的中间层级块，以提升短查询与长查询的向量搜索质量。随后在512词元块上使用重排序器进行相关性评分，确保上下文粒度适中。最终，将得分最高的中间块映射至2048词元的父块，为大语言模型提供足够规模的上下文支持。
原文摘要 · Abstract (English)
Retrieving the right level of context for a given query is a perennial challenge in information retrieval - too large a chunk dilutes semantic specificity, while chunks that are too small lack broader context. This paper introduces the Hierarchical Re-ranker Retriever (HRR), a framework designed to achieve both fine-grained and high-level context retrieval for large language model (LLM) applications. In HRR, documents are split into sentence-level and intermediate-level (512 tokens) chunks to maximize vector-search quality for both short and broad queries. We then employ a reranker that operates on these 512-token chunks, ensuring an optimal balance neither too coarse nor too fine for robust relevance scoring. Finally, top-ranked intermediate chunks are mapped to parent chunks (2048 tokens) to provide an LLM with sufficiently large context.
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。