用哈希技术加速检索，让大模型问答更快更准。
HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generation
- 直接生成查询哈希码，跳过特征提取，大幅降耗。
- 检索速度提升90%，准确率接近传统方法，问答得分高1.4%-4.3%。
- 适合需要快速响应的海量知识问答场景，如智能客服。
检索增强生成（RAG）在面对大规模知识库时面临效率瓶颈，同时难以保持上下文相关性。我们提出 Hash-RAG 框架，将深度哈希技术与系统优化结合，解决上述问题。查询直接从知识库哈希码中学习二进制编码，省去中间特征提取步骤，显著降低存储与计算开销。在此高效哈希检索基础上，我们实现细粒度分块，并设计提示引导的块到上下文模块（PGCC），通过提示工程融合检索到的哈希索引命题及其原始文档片段，提升大模型上下文感知能力。在 NQ、TriviaQA 与 HotpotQA 数据集上的实验表明，本方法相较传统方案检索时间减少 90%，召回性能仍保持良好，且在 EM 分数上优于检索/非检索基线 1.4%-4.3%。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) encounters efficiency challenges when scaling to massive knowledge bases while preserving contextual relevance. We propose Hash-RAG, a framework that integrates deep hashing techniques with systematic optimizations to address these limitations. Our queries directly learn binary hash codes from knowledgebase code, eliminating intermediate feature extraction steps, and significantly reducing storage and computational overhead. Building upon this hash-based efficient retrieval framework, we establish the foundation for fine-grained chunking. Consequently, we design a Prompt-Guided Chunk-to-Context (PGCC) module that leverages retrieved hash-indexed propositions and their original document segments through prompt engineering to enhance the LLM's contextual awareness. Experimental evaluations on NQ, TriviaQA, and HotpotQA datasets demonstrate that our approach achieves a 90% reduction in retrieval time compared to conventional methods while maintaining considerate recall performance. Additionally, The proposed system outperforms retrieval/non-retrieval baselines by 1.4-4.3% in EM scores.
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。