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

TL;DR

This paper introduces a blockchain-based framework for secure, efficient cross-silo knowledge sharing to improve large language model performance and address hallucination issues.

Contribution

It presents a novel blockchain-supported system for coordinating dispersed knowledge silos, ensuring data security, quality, and incentivizing participation.

Findings

Effective knowledge sharing across silos demonstrated

Improved LLM retrieval accuracy shown in experiments

Enhanced data security and participant incentives implemented

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.