无需LLM摘要的树导航：长文档问答分层检索的匹配成本研究
原标题：Tree Navigation Without LLM Summaries: A Matched-Cost Study of Hierarchical Retrieval for Long-Document QA
AI 摘要
该论文提出 NavTree，一种仅使用叶节点的分层检索器，在长文档问答中不依赖 LLM 生成摘要，而是用确定性平衡段树作为导航结构。在匹配成本评估中，NavTree 在分层检索器中表现最强，并在多跳问答上显著优于 BM25，且索引阶段零 LLM 调用。研究还发现，摘要树的主要收益来自导航而非摘要内容本身，摘要节点在多块预算下反而会挤占不同子树的叶节点。
正文节选
Tree Navigation Without LLM Summaries: A Matched-Cost Study of Hierarchical Retrieval for Long-Document QA Abstract Retrieval-augmented generation grounds language models in external context, but for long documents flat top- retrieval can cluster on a single region and miss complementary evidence. RAPTOR-style summary trees address this by recursively clustering chunks and using a language model to summarize each cluster at indexing time, then ranking summary nodes alongside raw chunks at query