Connecting Large Language Models with Blockchain: Advancing the Evolution of Smart Contracts from Automation to Intelligence

TL;DR

The paper addresses the gap in smart contracts lacking intelligent reasoning by linking LLMs with blockchain data through the C-LLM framework. It combines semantic relatedness with truth discovery via the SenteTruth method to aggregate textual outputs from multiple LLMs and oracle nodes, even under adversarial conditions. Experimental results on a dataset of 10 oracle nodes and 5 LLMs show that SenteTruth improves data accuracy by an average of 17.74% over baselines when up to 40% of nodes are malicious, validating the approach. The work advances the integration of AI and blockchain, enabling more intelligent, adaptable smart contracts and outlining directions for broader applications and future enhancements.

Abstract

Blockchain smart contracts have catalyzed the development of decentralized applications across various domains, including decentralized finance. However, due to constraints in computational resources and the prevalence of data silos, current smart contracts face significant challenges in fully leveraging the powerful capabilities of Large Language Models (LLMs) for tasks such as intelligent analysis and reasoning. To address this gap, this paper proposes and implements a universal framework for integrating LLMs with blockchain data, {\sysname}, effectively overcoming the interoperability barriers between blockchain and LLMs. By combining semantic relatedness with truth discovery methods, we introduce an innovative data aggregation approach, {\funcname}, which significantly enhances the accuracy and trustworthiness of data generated by LLMs. To validate the framework's effectiveness, we construct a dataset consisting of three types of questions, capturing Q\&A interactions between 10 oracle nodes and 5 LLM models. Experimental results demonstrate that, even with 40\% malicious nodes, the proposed solution improves data accuracy by an average of 17.74\% compared to the optimal baseline. This research not only provides an innovative solution for the intelligent enhancement of smart contracts but also highlights the potential for deep integration between LLMs and blockchain technology, paving the way for more intelligent and complex applications of smart contracts in the future.

Figures (8)

• Figure 1: Obstacles to the intelligentization of smart contracts.
• Figure 2: The repetition rate of answer indicates the highest proportion of identical answers generated by the LLM for the same question when LLM API request parameters were set as "temperature=0, top_p=0, seed=42".
• Figure 3: The system flow of C-LLM.
• Figure 4: Details of SenteTruth.
• Figure 5: The influence of different models and problem types on data consistency.