HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915319633674240 |
|---|---|
| author | Guo, Jinyu Chen, Xunlei Xia, Qiyang Wang, Zhaokun Ou, Jie Qin, Libo Yao, Shunyu Tian, Wenhong |
| author_facet | Guo, Jinyu Chen, Xunlei Xia, Qiyang Wang, Zhaokun Ou, Jie Qin, Libo Yao, Shunyu Tian, Wenhong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_16133 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generation Guo, Jinyu Chen, Xunlei Xia, Qiyang Wang, Zhaokun Ou, Jie Qin, Libo Yao, Shunyu Tian, Wenhong Information Retrieval 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. |
| title | HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2505.16133 |