mlsanityData to 14 Oct 2026

Local Hybrid Retrieval-Augmented Document QA

arXiv 2511.10297 ↗First posted 13 Nov 2025cs.CLcited by 1

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Organizations handling sensitive documents face a critical dilemma: adopt cloud-based AI systems that offer powerful question-answering capabilities but compromise data privacy, or maintain local processing that ensures security but delivers poor accuracy. We present a question-answering system that resolves this trade-off by combining semantic understanding with keyword precision, operating entirely on local infrastructure without internet access. Our approach demonstrates that organizations can achieve competitive accuracy on complex queries across legal, scientific, and conversational documents while keeping all data on their machines. By balancing two complementary retrieval strategies and using consumer-grade hardware acceleration, the system delivers reliable answers with minimal errors, letting banks, hospitals, and law firms adopt conversational document AI without transmitting proprietary information to external providers. This work establishes that privacy and performance need not be mutually exclusive in enterprise AI deployment.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 5 of its 16 references that are in the map. First posted on arXiv 13 Nov 2025.

Builds on

5 of 16 references.

References · 5

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  4. 2017Billion-scale similarity search with GPUscited by 2,497
  5. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026CUBO: Self-Contained Retrieval-Augmented Generation on Consumer Laptops 10 GB Corpora, 16 GB RAM, Single-Device Deploymentcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026As We May Search
  2. 2025eSapiens's DEREK Module: Deep Extraction & Reasoning Engine for Knowledge with LLMs
  3. 2026Cloud and On-Premises Deployment of Uzbek Legal RAG via Targeted Retriever Fine-Tuning
  4. 2024LocalRQA: From Generating Data to Locally Training, Testing, and Deploying Retrieval-Augmented QA Systems
  5. 2026Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QA
  6. 2025From Documents to Dialogue: Building KG-RAG Enhanced AI Assistants
  7. 2026An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation
  8. 2025eSapiens: A Real-World NLP Framework for Multimodal Document Understanding and Enterprise Knowledge Processing