用大模型迭代生成关键词，让检索增强生成更准更可解释。
IterKey: Iterative Keyword Generation with LLMs for Enhanced Retrieval Augmented Generation
- 用大模型分三步：生成关键词、生成答案、验证答案，失败就重来。
- 在4个问答任务中，比传统BM25方法准确率高5%到20%。
- 既保持稀疏检索的可解释性，又接近密集检索的精度，适合需要透明性的场景。
检索增强生成（RAG）通过整合外部文档来弥补大语言模型（LLM）的上下文知识。然而，真实应用不仅要求高精度，还要求可解释性。稠密检索方法虽精度高，但缺乏可解释性；稀疏检索虽透明，却因依赖关键词匹配，常无法捕捉查询全貌。为此，我们提出IterKey，一种基于大模型的迭代关键词生成框架，通过稀疏检索增强RAG。IterKey包含三个由大模型驱动的阶段：生成用于检索的关键词，基于检索到的文档生成答案，以及验证答案。若验证失败，则以优化后的关键词重新迭代。在四个问答任务上，实验结果表明，IterKey相比基于BM25的RAG和简单基线，准确率提升5%至20%。其性能与基于稠密检索的RAG及先前使用稠密模型的迭代查询优化方法相当。总之，IterKey是一种新颖的基于BM25的RAG方法，利用大模型迭代优化，有效平衡了精度与可解释性。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) has emerged as a way to complement the in-context knowledge of Large Language Models (LLMs) by integrating external documents. However, real-world applications demand not only accuracy but also interpretability. While dense retrieval methods provide high accuracy, they lack interpretability; conversely, sparse retrieval methods offer transparency but often fail to capture the full intent of queries due to their reliance on keyword matching. To address these issues, we introduce IterKey, an LLM-driven iterative keyword generation framework that enhances RAG via sparse retrieval. IterKey consists of three LLM-driven stages: generating keywords for retrieval, generating answers based on retrieved documents, and validating the answers. If validation fails, the process iteratively repeats with refined keywords. Across four QA tasks, experimental results show that IterKey achieves 5% to 20% accuracy improvements over BM25-based RAG and simple baselines. Its performance is comparable to dense retrieval-based RAG and prior iterative query refinement methods using dense models. In summary, IterKey is a novel BM25-based approach leveraging LLMs to iteratively refine RAG, effectively balancing accuracy with interpretability.
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。