PromptDEX:基于区块链的大模型提示词服务平台

doi:10.19678/j.issn.1000-3428.0070735

摘要/Abstract

摘要： 近年来,大模型已经成为人类生活的重要工具之一。作为人类与大模型沟通的桥梁,提示词发挥着至关重要的作用。虽然高质量提示词能够充分激发大模型的潜力,但其设计不仅需要专业技能,还需耗费大量资源,这促使提示词交易市场以及授权服务模式的出现。然而,将提示词作为商品存在以下3个问题:1)提示词明文一旦泄露就会被轻易地复制以及传播,使其失去价值;2)缺乏客观的提示词质量标准和价格体系;3)用户难以对虚假提示词的提供者追究责任,同时中心化平台的行为也会影响提供者的权益。针对上述挑战,本文提出了PromptDEX,一种基于区块链的大模型提示词服务平台。基于智能合约的提示词租用机制和基于LangChain的服务模板,使提供者直接与需求方对接,削弱中心化机构对参与者利益和隐私的影响。所有交易记录将被公开透明地记录在链上,确保交易流程安全、可靠、可追责。此外,平台还设计了以需求方评分为依据的动态定价机制。实验结果表明,PromptDEX引入区块链所带来的额外成本开销以角为单位计算,几乎可以忽略不计。提供者仅需约10行代码即可构建API服务,对于网络带宽要求极低,具备较强的可行性与实用性。

关键词: 区块链, 大模型, 提示词, LangChain, 隐私保护, 智能合约

Abstract: In recent years, large models have become one of the most important tools for humans. Prompts play a crucial role as bridges of communication between humans and large models. Although high-quality prompts can fully unleash the potential of large models, their design requires both specialized skills and substantial resources, leading to the emergence of prompt trading markets and licensing service models. However, treating prompts as commodities presents three main challenges: 1) Loss of value of prompts owing to them being easily copied and disseminated once the prompt text is leaked; 2) Lack of objective standards and pricing systems to ensure prompt quality; 3) Difficulty experienced by users in holding providers of false prompts accountable, and rights of providers being affected by the actions of centralized platforms. To address these challenges, this study proposes PromptDEX, a blockchain-based service platform for large model prompts. Through a prompt rental mechanism based on smart contracts and service templates built on LangChain, the platform enables direct interaction between providers and demanders, thereby reducing the impact of centralized institutions on interests and privacy of the participants. All transaction records are transparently stored in the blockchain to ensure security, reliability, and accountability. Additionally, a dynamic pricing mechanism based on demand-side ratings is implemented. The experimental results show that the additional cost incurred by integrating the blockchain is negligible, as calculated in terms of fractions of a cent. Providers can build API services with only approximately 10 lines of code, requiring minimal network bandwidth and demonstrating strong feasibility and practicality.

Key words: blockchain, large model, prompt, LangChain, privacy protection, smart contract

中图分类号:

TP391

张凌浩, 谭海波, 赵赫, 陈中. PromptDEX:基于区块链的大模型提示词服务平台[J]. 计算机工程, 2026, 52(10): 375-389.

ZHANG Linghao, TAN Haibo, ZHAO He, CHEN Zhong. PromptDEX: Blockchain-Based Servicing Platform for Large Model Prompt[J]. Computer Engineering, 2026, 52(10): 375-389.

https://www.ecice06.com/CN/Y2026/V52/I10/375

参考文献

[1] FLORIDI L, CHIRIATTI M. GPT-3: its nature, scope, limits, and consequences[J]. Minds and Machines, 2020, 30(4): 681-694.
[2] LIU Y X, ZHANG K, LI Y, et al. Sora: a review on background, technology, limitations, and opportunities of large vision models[EB/OL].[2024-11-18]. https://arxiv.org/pdf/2402.17177.
[3] OpenAI. Number of ChatGPT users (Dec 2024) [EB/OL]. [2024-11-18]. https://explodingtopics.com/blog/chatgpt-users.
[4] DENG M K, WANG J Y, HSIEH C P, et al. RLPrompt: optimizing discrete text prompts with reinforcement learning[EB/OL]. [2024-11-18]. https://arxiv.org/abs/2205.12548.
[5] SHIN T, RAZEGHI Y, IV R L L, et al. Autoprompt: eliciting knowledge from language models with automatically generated prompts[EB/OL].[2024-11-18]. https://arxiv.org/pdf/2010.15980.
[6] BIESTER F, DEL GAUDIO D D, ABDELAAL M. Enhancing knowledge base construction from pre-trained language models using prompt ensembles[C]//Proceedings of KBC-LM/LM-KBC@ ISWC. 2023. Athens, Greece: CEUR Workshop Proceedings, 2023:106-110.
[7] YAO H W, LOU J, QIN Z, et al. PromptCARE: prompt copyright protection by watermark injection and verification[C]//Proceedings of the IEEE Symposium on Security and Privacy (SP). Washington D.C., USA: IEEE Press, 2024: 845-861.
[8] REN H L, YAN A L, GAO C Z, et al. Are you copying my prompt? protecting the copyright of vision prompt for VPaaS via watermark[EB/OL]. [2024-11-18]. https://arxiv.org/abs/2405.15161.
[9] ZHENG Z B, XIE S A, DAI H N, et al. Blockchain challenges and opportunities: a survey[J]. International Journal of Web and Grid Services, 2018, 14(4): 352.
[10] MOHANTA B K, PANDA S S, JENA D. An overview of smart contract and use cases in blockchain technology[C]//Proceedings of the 9th International Conference on Computing, Communication and Networking Technologies (ICCCNT). Washington D.C., USA: IEEE Press, 2018: 1-4.
[11] 王群, 李馥娟, 倪雪莉, 等. 区块链数据形成与隐私威胁[J]. 计算机工程, 2023, 49(8): 1-12. WANG Q, LI F J, NI X L, et al. Data formation and privacy threat of blockchain[J]. Computer Engineering, 2023, 49(8): 1-12. (in Chinese)
[12] 旋逸昭, 赵红武, 金瑜. 一种基于双链的区块链共识机制[J]. 计算机工程, 2024, 50(5): 139-148. XUAN Y Z, ZHAO H W, JIN Y. A dual-chain-based consensus mechanism for blockchain[J]. Computer Engineering, 2024, 50(5): 139-148. (in Chinese)
[13] 倪雪莉, 马卓, 王群. 区块链矿池网络及典型攻击方式综述[J]. 计算机工程, 2024, 50(1): 17-29. NI X L, MA Z, WANG Q. Overview of blockchain mining pool networks and typical attack modes[J]. Computer Engineering, 2024, 50(1): 17-29. (in Chinese)
[14] GERVAIS A, KARAME G O, WVST K, et al. On the security and performance of proof of work blockchains[C]//Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security. New York, USA: ACM Press, 2016: 3-16.
[15] MASLA N, VYAS V, GAUTAM J, et al. Reduction in gas cost for blockchain enabled smart contract[C]//Proceedings of the IEEE 4th International Conference on Computing, Power and Communication Technologies (GUCON). Washington D.C., USA: IEEE Press, 2021: 1-6.
[16] 王东清,芦飞,张炳会,等.大语言模型中提示词工程综述[J].计算机系统应用,2025,34(1):1-10. WANG D Q, LU F, ZHANG B H, et al. Survey on prompt engineering in large language model[J]. Computer Systems & Applications, 2025,34(1):1-10.(in Chinese)
[17] GU S S, IWASAWA Y, KOJIMA T, et al. Large language models are zero-shot reasoners[C]//Proceedings of the Advances in Neural Information Processing Systems 35. Louisiana, USA: Neural Information Processing Systems Foundation, Inc. (NeurIPS), 2022: 22199-22213.
[18] CAO Y, GRIFFITHS T, NARASIMHAN K, et al. Tree of thoughts: deliberate problem solving with large language models[C]//Proceedings of the Advances in Neural Information Processing Systems 36. Louisiana, USA: Neural Information Processing Systems Foundation, Inc. (NeurIPS), 2023: 11809-11822.
[19] BESTA M, BLACH N, KUBICEK A, et al. Graph of thoughts: solving elaborate problems with large language models[C]//Proceedings of the 38th AAAI Conference on Artificial Intelligence. Vancouver, USA: AAAI Press, 2024: 17682-17690.
[20] TOPSAKAL O, AKINCI T C. Creating large language model applications utilizing LangChain: a primer on developing LLM apps fast[C]//Proceedings of International Conference on Applied Engineering and Natural Sciences, New York, USA: [s.n], 2023: 1050-1056.
[21] DU Y P, YIN Z H, XIE R F, et al. Prompt template construction by average gradient search with external knowledge for aspect sentimental analysis[J]. Expert Systems with Applications, 2024, 238: 122271.
[22] FLEISCHHACKER N, JAGER T, SCHRÖDER D. On tight security proofs for schnorr signatures[C]//Proceedings of the 20th International Conference on the Theory and Application of Cryptology and Information Security. Berlin, Germany: Springer, 2014: 512-531.
[23] ZHANG Q X. An overview and analysis of hybrid encryption: the combination of symmetric encryption and asymmetric encryption[C]//Proceedings of the 2nd International Conference on Computing and Data Science (CDS). Washington D.C., USA: IEEE Press, 2021: 616-622.
[24] BrambleXu. MovieLens 1M dataset [EB/OL]. [2024-11-18].https://github.com/BrambleXu/pydata-notebook/blob/master/datasets/movielens/ratings.dat.
[25] JAIN S M. Introduction to Remix IDE[M]//A Brief Introduction to Web 3: Decentralized Web Fundamentals for App Development. Berlin, Gemany: Springer, 2022: 89-126.
[26] KALODNER H, GOLDFEDER S, CHEN X Q, et al. Arbitrum: scalable, private smart contracts[EB/OL]. [2024-11-18]. https://www.usenix.org/system/files/conference/usenixsecurity18/sec18-kalodner.pdf.
[27] DA SILVA E J L A, DE ARAJO C S, DA SILVA J M Jr, et al. Development of cryptogames with unity on an ethereum blockchain test network: case study and challenges[J]. Journal on Interactive Systems, 2024, 15(1): 549-560.
[28] BARRAULT L, BOJAR O, COSTA-JUSSÀ M R, et al. Findings of the 2019 conference on machine translation (WMT19)[C]//Proceedings of the 4th Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1). Stroudsburg, USA: ACL, 2019: 1-61.
[29] ZHAO S J, O’MAHONY D. Applying blockchain Layer2 technology to mass e-commerce[EB/OL]. [2024-11-18]. https://eprint.iacr.org/2020/502.
[30] Optimism. OP Mainet blockchain explorer [EB/OL]. [2024-11-18]. https://optimism.blockscout.com.
[31] Arbitrum. Arbitrum one blockchain explorer [EB/OL]. [2024-11-18]. https://arbitrum.blockscout.com.

选择文件类型/文献管理软件名称

选择包含的内容