Automated Translation of Legal Instruments to Smart Contracts Using Large Language Models
Guardado en:
| Publicado en: | ProQuest Dissertations and Theses (2025) |
|---|---|
| Autor principal: | |
| Publicado: |
ProQuest Dissertations & Theses
|
| Materias: | |
| Acceso en línea: | Citation/Abstract Full Text - PDF |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3202665185 | ||
| 003 | UK-CbPIL | ||
| 020 | |a 9798314878460 | ||
| 035 | |a 3202665185 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 084 | |a 66569 |2 nlm | ||
| 100 | 1 | |a Radic, Nikola | |
| 245 | 1 | |a Automated Translation of Legal Instruments to Smart Contracts Using Large Language Models | |
| 260 | |b ProQuest Dissertations & Theses |c 2025 | ||
| 513 | |a Dissertation/Thesis | ||
| 520 | 3 | |a The convergence of blockchain and legal technology has spurred interest in smart legal contracts, translating natural-language agreements into self-executing code. This thesis addresses the challenge of automating the translation process using a large language model. It focuses on Horizon Europe consortium agreements – complex, multiparty research contracts – and their implementation as decentralized autonomous organizations on a Hyperledger Fabric blockchain. The motivation arises from the significant time and expertise required to convert legal terms into secure smart contracts manually. The research aims to bridge the gap between legal text and operational code by leveraging advanced natural language processing and artificial intelligence techniques. It does so by developing a test-driven pipeline that takes legal clauses as input and produces validated smart contract code as output. The methodology integrates a large language model to interpret and transform contractual language into chaincode functions. At the same time, a suite of automated tests derived from the contract’s provisions ensures the fidelity and correctness of the generated code. By adopting principles from software engineering (such as behavior and test-driven development) in the legal context, the pipeline runs pre-written unit tests on the generated code to ensure its functionality and further improve it. This approach is demonstrated through a Horizon Europe case study, translating consortium agreement clauses (e.g., intellectual property rights, payment terms, liability) into self-executing Fabric chaincode. Significantly, the research contributes a framework for reducing ambiguity and enforcing legal compliance in smart contracts. It highlights both the promise and current limitations of state-of-the-art large language models in legal applications, showcasing a novel intersection of artificial intelligence and law: using large language models, complemented by robust automated testing, to reliably automate the generation of executable smart contracts based on legal agreements, paving the way for more trustworthy and efficient consortium governance in Horizon Europe and beyond.  | |
| 653 | |a Computer science | ||
| 653 | |a Law | ||
| 653 | |a Artificial intelligence | ||
| 653 | |a Computer engineering | ||
| 773 | 0 | |t ProQuest Dissertations and Theses |g (2025) | |
| 786 | 0 | |d ProQuest |t ProQuest Dissertations & Theses Global | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3202665185/abstract/embedded/H09TXR3UUZB2ISDL?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3202665185/fulltextPDF/embedded/H09TXR3UUZB2ISDL?source=fedsrch |