通过迭代反馈优化，让大模型更准地回答复杂问题。
KGiRAG: An Iterative GraphRAG Approach for Responding Sensemaking Queries
- 用图结构+反馈机制反复修正答案，逐步逼近正确结果。
- 在HotPotQA数据集上，回答的语义质量和相关性显著提升。
- 适合需要深度推理和事实验证的复杂问答场景。
近期研究显示，基于图结构的大型语言模型（LLM）检索增强生成（RAG）方法在回答各类复杂查询方面具有潜力，尤其适用于超出模型先验知识范围的问题。然而，大模型容易产生幻觉，且在处理足够大的上下文以有效支撑复杂查询时存在技术瓶颈。为此，我们提出一种新型的迭代式、反馈驱动的GraphRAG架构，利用响应质量评估机制，持续迭代优化输出，直至生成逻辑严谨、依据充分的回答。在HotPotQA数据集上的实验表明，该迭代RAG策略相较于单次生成基线，在语义质量和相关性方面均有明显提升。
原文摘要 · Abstract (English)
Recent literature highlights the potential of graph-based approaches within large language model (LLM) retrieval-augmented generation (RAG) pipelines for answering queries of varying complexity, particularly those that fall outside the LLM's prior knowledge. However, LLMs are prone to hallucination and often face technical limitations in handling contexts large enough to ground complex queries effectively. To address these challenges, we propose a novel iterative, feedback-driven GraphRAG architecture that leverages response quality assessment to iteratively refine outputs until a sound, well-grounded response is produced. Evaluating our approach with queries from the HotPotQA dataset, we demonstrate that this iterative RAG strategy yields responses with higher semantic quality and improved relevance compared to a single-shot baseline.
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。