KnowTrace：利用结构化知识追踪引导迭代检索增强生成
KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge Tracing
AI总结：
KnowTrace通过结构化知识图谱追踪替代简单上下文堆叠，缓解RAG中的上下文过载，并利用知识回溯生成过程监督数据实现自我引导，在多跳问答基准上显著超越现有方法。
摘要：
检索增强生成（RAG）的最新进展为大型语言模型（LLM）提供了对相关信息的迭代检索，以处理复杂的多跳问题。这些方法通常在LLM推理和检索之间交替进行，将外部信息累积到LLM的上下文中。然而，不断增长的上下文本质上给LLM感知关键信息片段之间联系带来了越来越大的负担，而无效的推理步骤进一步加剧了这一过载问题。在本文中，我们提出了KnowTrace，一个优雅的RAG框架，旨在（1）缓解上下文过载和（2）引导更高质量的多步推理。KnowTrace不是简单堆叠检索到的内容，而是自主追踪出所需的知识三元组，以组织一个与输入问题相关的特定知识图谱。这种结构化工作流不仅赋予LLM一个可理解的推理上下文，还自然地启发了知识回溯的反思机制，将有助于贡献的LLM生成识别为过程监督数据，用于自我引导。大量实验表明，KnowTrace在三个多跳问答基准上始终优于现有方法，且引导版本进一步放大了增益。
英文摘要：
Recent advances in retrieval-augmented generation (RAG) furnish large language models (LLMs) with iterative retrievals of relevant information to handle complex multi-hop questions. These methods typically alternate between LLM reasoning and retrieval to accumulate external information into the LLM's context. However, the ever-growing context inherently imposes an increasing burden on the LLM to perceive connections among critical information pieces, with futile reasoning steps further exacerbating this overload issue. In this paper, we present KnowTrace, an elegant RAG framework to (1) mitigate the context overload and (2) bootstrap higher-quality multi-step reasoning. Instead of simply piling the retrieved contents, KnowTrace autonomously traces out desired knowledge triplets to organize a specific knowledge graph relevant to the input question. Such a structured workflow not only empowers the LLM with an intelligible context for inference, but also naturally inspires a reflective mechanism of knowledge backtracing to identify contributive LLM generations as process supervision data for self-bootstrapping. Extensive experiments show that KnowTrace consistently surpasses existing methods across three multi-hop question answering benchmarks, and the bootstrapped version further amplifies the gains.
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。
