BLOCKS: Blockchain-supported Cross-Silo Knowledge Sharing for Efficient LLM Services

2025-06-26

AI Summary

To address the pervasive hallucination problem in large language models (LLMs) and the fragmentation of downstream knowledge across isolated, privacy- and security-constrained private sources, this paper proposes a blockchain-based cross-silo knowledge sharing framework. The framework employs knowledge distillation and prompt engineering for secure knowledge encapsulation; implements smart-contract-driven knowledge trading and provenance recording, coupled with decentralized storage to preserve data sovereignty; integrates a reputation system and multi-source cross-validation to enhance knowledge credibility; and provides a scalable query-generation API for efficient retrieval. Experimental results demonstrate that the framework significantly improves retrieval accuracy and response latency in heterogeneous, multi-source knowledge environments, thereby strengthening LLMs’ robust external knowledge integration capability. It establishes a novel paradigm for trustworthy, incentive-compatible knowledge sharing.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

The hallucination problem of Large Language Models (LLMs) has increasingly drawn attention. Augmenting LLMs with external knowledge is a promising solution to address this issue. However, due to privacy and security concerns, a vast amount of downstream task-related knowledge remains dispersed and isolated across various "silos," making it difficult to access. To bridge this knowledge gap, we propose a blockchain-based external knowledge framework that coordinates multiple knowledge silos to provide reliable foundational knowledge for large model retrieval while ensuring data security. Technically, we distill knowledge from local data into prompts and execute transactions and records on the blockchain. Additionally, we introduce a reputation mechanism and cross-validation to ensure knowledge quality and provide incentives for participation. Furthermore, we design a query generation framework that provides a direct API interface for large model retrieval. To evaluate the performance of our proposed framework, we conducted extensive experiments on various knowledge sources. The results demonstrate that the proposed framework achieves efficient LLM service knowledge sharing in blockchain environments.

Problem

• Addresses LLM hallucination via external knowledge sharing
• Solves isolated knowledge silos with blockchain security
• Ensures knowledge quality via reputation and cross-validation

Innovation

• Blockchain-based knowledge framework for LLMs
• Reputation mechanism ensures knowledge quality
• API interface for direct model retrieval