HIRO：分层信息检索优化
HIRO: Hierarchical Information Retrieval Optimization
AI总结：
HIRO提出基于深度优先搜索和分支剪枝的分层信息检索优化方法，在减少LLM上下文信息过载的同时保持信息完整，并在NarrativeQA上取得10.85%的性能提升。
摘要：
检索增强生成（RAG）通过将外部知识动态整合到大语言模型（LLM）中，解决了其静态训练数据集的局限性，从而彻底改变了自然语言处理。近期RAG的实现利用了分层数据结构，这些结构在不同摘要层级和信息密度上组织文档。然而，这种复杂性可能导致大语言模型因信息过载而“卡顿”，从而需要更复杂的查询机制。在此背景下，我们提出了分层信息检索优化（HIRO），这是一种新颖的查询方法，采用基于深度优先搜索（DFS）的递归相似度分数计算和分支剪枝。该方法独特地在不损失信息的前提下最小化传递给大语言模型的上下文，有效应对了数据过多的挑战。HIRO的精炼方法通过在NarrativeQA数据集上实现10.85%的性能提升得到了验证。
英文摘要：
Retrieval-Augmented Generation (RAG) has revolutionized natural language processing by dynamically integrating external knowledge into Large Language Models (LLMs), addressing their limitation of static training datasets. Recent implementations of RAG leverage hierarchical data structures, which organize documents at various levels of summarization and information density. This complexity, however, can cause LLMs to "choke" on information overload, necessitating more sophisticated querying mechanisms. In this context, we introduce Hierarchical Information Retrieval Optimization (HIRO), a novel querying approach that employs a Depth-First Search (DFS)-based recursive similarity score calculation and branch pruning. This method uniquely minimizes the context delivered to the LLM without informational loss, effectively managing the challenge of excessive data. HIRO's refined approach is validated by a 10.85% improvement in performance on the NarrativeQA dataset.
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。
