重构上下文：评估检索增强生成的高级分块策略
Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation
AI总结：
本研究评估了RAG中late chunking与contextual retrieval两种高级分块策略，发现前者效率高但牺牲相关性，后者语义连贯性更好但计算成本更高。
摘要：
检索增强生成（RAG）已成为一种变革性方法，通过将大型语言模型（LLMs）的输出基于外部知识源来增强其能力。然而，一个关键问题依然存在：如何在LLMs的输入约束内有效管理海量外部知识？传统方法通过将外部文档分块为较小的固定大小段来解决此问题。虽然此方法缓解了输入限制，但常导致上下文碎片化，造成检索不完整和生成连贯性下降。为克服这些缺陷，引入了两种高级技术：late chunking和contextual retrieval，两者均旨在保留全局上下文。尽管潜力巨大，其比较优势与局限性仍不清晰。本研究对late chunking和contextual retrieval进行了严格分析，评估它们在优化RAG系统时的有效性与效率。结果表明，contextual retrieval更有效地保留了语义连贯性，但需要更多计算资源。相反，late chunking效率更高，但倾向于牺牲相关性和完整性。
英文摘要：
Retrieval-augmented generation (RAG) has become a transformative approach for enhancing large language models (LLMs) by grounding their outputs in external knowledge sources. Yet, a critical question persists: how can vast volumes of external knowledge be managed effectively within the input constraints of LLMs? Traditional methods address this by chunking external documents into smaller, fixed-size segments. While this approach alleviates input limitations, it often fragments context, resulting in incomplete retrieval and diminished coherence in generation. To overcome these shortcomings, two advanced techniques, late chunking and contextual retrieval, have been introduced, both aiming to preserve global context. Despite their potential, their comparative strengths and limitations remain unclear. This study presents a rigorous analysis of late chunking and contextual retrieval, evaluating their effectiveness and efficiency in optimizing RAG systems. Our results indicate that contextual retrieval preserves semantic coherence more effectively but requires greater computational resources. In contrast, late chunking offers higher efficiency but tends to sacrifice relevance and completeness.
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。
