mlsanityData to 14 Oct 2026

HaS: Accelerating RAG through Homology-Aware Speculative Retrieval

arXiv 2604.20452 ↗First posted 22 Apr 2026cs.IR cs.CLcited by 0

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) expands the knowledge boundary of large language models (LLMs) at inference by retrieving external documents as context. However, retrieval becomes increasingly time-consuming as the knowledge databases grow in size. Existing acceleration strategies either compromise accuracy through approximate retrieval, or achieve marginal gains by reusing results of strictly identical queries. We propose HaS, a homology-aware speculative retrieval framework that performs low-latency speculative retrieval over restricted scopes to obtain candidate documents, followed by validating whether they contain the required knowledge. The validation, grounded in the homology relation between queries, is formulated as a homologous query re-identification task: once a previously observed query is identified as a homologous re-encounter of the incoming query, the draft is deemed acceptable, allowing the system to bypass slow full-database retrieval. Benefiting from the prevalence of homologous queries under real-world popularity patterns, HaS achieves substantial efficiency gains. Extensive experiments demonstrate that HaS reduces retrieval latency by 23.74% and 36.99% across datasets with only a 1-2% marginal accuracy drop. As a plug-and-play solution, HaS also significantly accelerates complex multi-hop queries in modern agentic RAG pipelines. Source code is available at: https://github.com/ErrEqualsNil/HaS.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 32 of its 38 references that are in the map. First posted on arXiv 22 Apr 2026.

Builds on

32 of 38 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Accelerating Retrieval-Augmented Generation14 Dec
  2. 2024Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Models29 Nov
  3. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG8 Oct
  4. 2024Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworks26 Jul
  5. 2024Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting11 Jul
  6. 2024Corrective Retrieval Augmented Generation29 Jan

Other references · 26

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2023Mistral 7Bcited by 3,164
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  8. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  9. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  10. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  11. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  12. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 861
14 more
  1. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 578
  2. 2024The Faiss librarycited by 376
  3. 2021Simple Entity-Centric Questions Challenge Dense Retrieverscited by 140
  4. 2024xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Tokencited by 125
  5. 2024RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generationcited by 98
  6. 2024TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Textcited by 63
  7. 2024RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedbackcited by 46
  8. 2024IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologuescited by 40
  9. 2025Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generationcited by 36
  10. 2024Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selectioncited by 25
  11. 2024Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answerscited by 18
  12. 2024DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answeringcited by 14
  13. 2025Federated Retrieval Augmented Generation for Multi-Product Question Answeringcited by 10
  14. 2022Caching Historical Embeddings in Conversational Searchcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026DF-RAG: Query-Aware Diversity for Retrieval-Augmented Generation
  2. 2024CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversity
  3. 2026Scaling DPPs for RAG: Density Meets Diversity
  4. 2025RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation
  5. 2026L-RAG: Balancing Context and Retrieval with Entropy-Based Lazy Loading
  6. 2024Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks
  7. 2023Retrieval-Augmented Generation for Large Language Models: A Survey
  8. 2025Dynamic and Parametric Retrieval-Augmented Generation