mlsanityData to 14 Oct 2026

A Decentralized Retrieval Augmented Generation System with Source Reliabilities Secured on Blockchain

arXiv 2511.07577 ↗First posted 10 Nov 2025cs.CR cs.CL cs.IRcited by 1

On the map: Retrieval-augmented generation → Privacy and security of RAG

Abstract (arXiv)

Existing retrieval-augmented generation (RAG) systems typically use a centralized architecture, causing a high cost of data collection, integration, and management, as well as privacy concerns. There is a great need for a decentralized RAG system that enables foundation models to utilize information directly from data owners who maintain full control over their sources. However, decentralization brings a challenge: the numerous independent data sources vary significantly in reliability, which can diminish retrieval accuracy and response quality. To address this, our decentralized RAG system has a novel reliability scoring mechanism that dynamically evaluates each source based on the quality of responses it contributes to generate and prioritizes high-quality sources during retrieval. To ensure transparency and trust, the scoring process is securely managed through blockchain-based smart contracts, creating verifiable and tamper-proof reliability records without relying on a central authority. We evaluate our decentralized system with two Llama models (3B and 8B) in two simulated environments where six data sources have different levels of reliability. Our system achieves a +10.7% performance improvement over its centralized counterpart in the real world-like unreliable data environments. Notably, it approaches the upper-bound performance of centralized systems under ideally reliable data environments. The decentralized infrastructure enables secure and trustworthy scoring management, achieving approximately 56% marginal cost savings through batched update operations. Our code and system are open-sourced at github.com/yining610/Reliable-dRAG.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 16 of its 24 references that are in the map. First posted on arXiv 10 Nov 2025.

Builds on

16 of 24 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generation27 Apr
  2. 2024Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data20 Jun
  3. 2024The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)23 Feb

Other references · 13

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 139
  5. 2025AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systemscited by 90
  6. 2021Conditional probing: measuring usable information beyond a baselinecited by 62
  7. 2024TokenSHAP: Interpreting Large Language Models with Monte Carlo Shapley Value Estimationcited by 42
  8. 2024M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitionscited by 38
  9. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practicescited by 23
  10. 2024UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorizationcited by 17
  11. 2025LLM-Net: Democratizing LLMs-as-a-Service through Blockchain-based Expert Networkscited by 7
  12. 2025Federated Retrieval-Augmented Generation: A Systematic Mapping Studycited by 6
1 more
  1. 2025Decentralizing AI Memory: SHIMI, a Semantic Hierarchical Memory Index for Scalable Agent Reasoningcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026TrustRAG: Blockchain-Enhanced RAG via Committee-Based Credibility Scoringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Engineering the RAG Stack: A Comprehensive Review of the Architecture and Trust Frameworks for Retrieval-Augmented Generation Systems
  2. 2025Provably Secure Retrieval-Augmented Generation
  3. 2025Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval
  4. 2024Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents
  5. 2026Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks
  6. 2025Securing RAG: A Risk Assessment and Mitigation Framework
  7. 2024C-FedRAG: A Confidential Federated Retrieval-Augmented Generation System
  8. 2024Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases