Optimizing Large Language Models to Expedite the Development of Smart Contracts
Not on the map. Why?
Abstract (arXiv)
Programming has always been at the heart of technological innovation in the 21st century. With the advent of blockchain technologies and the proliferation of web3 paradigms of decentralised applications, smart contracts have been very instrumental in enabling developers to build applications that reside on decentralised blockchains. Despite the huge interest and potential of smart contracts, there is still a significant knowledge and skill gap that developers need to cross in order to build web3 applications. In light of this, we introduce MazzumaGPT, a large language model that has been optimised to generate smart contract code and aid developers to scaffold development and improve productivity. As part of this research, we outline the optimisation and fine-tuning parameters, evaluate the model's performance on functional correctness and address the limitations and broader impacts of our research.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 30 of its 49 references that are in the map. First posted on arXiv 8 Oct 2023.
Builds on
30 of 49 references.
References · 30
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2021Evaluating Large Language Models Trained on Codecited by 8,053
- 2020Scaling Laws for Neural Language Modelscited by 6,411
- 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
- 2021Program Synthesis with Large Language Modelscited by 3,509
- 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,829
- 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,718
- 2022Competition-Level Code Generation with AlphaCodecited by 1,427
- 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
- 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
- 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
- 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
18 more
- 2018Universal Transformerscited by 613
- 2022InCoder: A Generative Model for Code Infilling and Synthesiscited by 492
- 2020CodeBLEU: a Method for Automatic Evaluation of Code Synthesiscited by 468
- 2023The Curse of Recursion: Training on Generated Data Makes Models Forgetcited by 343
- 2022CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learningcited by 342
- 2020Unsupervised Translation of Programming Languagescited by 262
- 2019SPoC: Search-based Pseudocode to Codecited by 176
- 2016DeepCoder: Learning to Write Programscited by 145
- 2015Neural GPUs Learn Algorithmscited by 118
- 2014Learning to Executecited by 105
- 2015Neural Programmer-Interpreterscited by 96
- 2020PyMT5: multi-mode translation of natural language and Python code with transformerscited by 80
- 2021Learning to Synthesize Programs as Interpretable and Generalizable Policiescited by 59
- 2017Neural Machine Translation and Sequence-to-sequence Models: A Tutorialcited by 25
- 2021Learning to Complete Code with Sketchescited by 23
- 2023AI-assisted Code Authoring at Scale: Fine-tuning, deploying, and mixed methods evaluationcited by 20
- 2019Learning Compositional Neural Programs with Recursive Tree Search and Planningcited by 17
- 2022CodexDB: Generating Code for Processing SQL Queries using GPT-3 Codexcited by 5
Built on by
Citing papers per year: 2025: 1.
1 paper.