# Repository-Level Solidity Code Generation with Large Language Models: From Prompting to Fine-Tuning

arXiv: https://arxiv.org/abs/2606.19988 · HTML: https://mlsanity.com/paper/2606.19988/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 44 of its 77 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Placed in

- Retrieval-augmented generation / [Privacy and security of RAG](https://mlsanity.com/rag/privacy-and-security-of-rag/)

## Builds on (most cited first, 30 of 44)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [CodeSearchNet Challenge: Evaluating the State of Semantic Code Search](https://mlsanity.com/paper/1909.09436/) (2019)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection](https://mlsanity.com/paper/2403.03507/) (2024)
- [MetaICL: Learning to Learn In Context](https://mlsanity.com/paper/2110.15943/) (2021)
- [Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping](https://mlsanity.com/paper/2002.06305/) (2020)
- [RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems](https://mlsanity.com/paper/2306.03091/) (2023)
- [DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence](https://mlsanity.com/paper/2406.11931/) (2024)
- [On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines](https://mlsanity.com/paper/2006.04884/) (2020)
- [VeriGen: A Large Language Model for Verilog Code Generation](https://mlsanity.com/paper/2308.00708/) (2023)
- [TACO: Topics in Algorithmic COde generation dataset](https://mlsanity.com/paper/2312.14852/) (2023)
- [CodePlan: Repository-level Coding using LLMs and Planning](https://mlsanity.com/paper/2309.12499/) (2023)
- [Structured Chain-of-Thought Prompting for Code Generation](https://mlsanity.com/paper/2305.06599/) (2023)
- [CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code](https://mlsanity.com/paper/2302.05527/) (2023)
- [Slither: A Static Analysis Framework For Smart Contracts](https://mlsanity.com/paper/1908.09878/) (2019)
- [Grammar Prompting for Domain-Specific Language Generation with Large Language Models](https://mlsanity.com/paper/2305.19234/) (2023)
- [On the Effectiveness of Large Language Models in Domain-Specific Code Generation](https://mlsanity.com/paper/2312.01639/) (2023)
- [Language Models for Code Completion: A Practical Evaluation](https://mlsanity.com/paper/2402.16197/) (2024)
- [A Deep Dive into Large Language Models for Automated Bug Localization and Repair](https://mlsanity.com/paper/2404.11595/) (2024)
- [Empirical Review of Automated Analysis Tools on 47,587 Ethereum Smart Contracts](https://mlsanity.com/paper/1910.10601/) (2019)
- [Chain-of-Thought in Neural Code Generation: From and For Lightweight Language Models](https://mlsanity.com/paper/2312.05562/) (2023)
- [Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner](https://mlsanity.com/paper/2305.01711/) (2023)

## Abstract (arXiv)

Large Language Models (LLMs) have shown strong capabilities in general-purpose code generation, but their effectiveness in specialized software domains remains underexplored. Solidity smart contracts represent a high-stakes domain where generated code must satisfy strict language-level, security, and software-engineering constraints. Existing benchmarks and metrics remain insufficient for repository-level Solidity generation, where models must synthesize complete contracts from natural language requirements. To address this gap, we introduce SolidityBench, a benchmark of 5,470 repository-level Solidity smart contracts paired with natural language descriptions. We also propose SolidityScore, a Solidity-aware semantic metric that emphasizes domain-critical constructs such as security modifiers, contract declarations, and Solidity-specific keywords. Using this benchmark, we evaluate representative code LLMs, including Qwen2.5-Coder, DeepSeek-Coder, and CodeLlama, across zero-shot prompting, Chain-of-Thought reasoning, in-context learning, retrieval-augmented generation, and supervised fine-tuning. The results show that general-purpose models exhibit systematic structural deficiencies in repository-level Solidity generation. Among non-parametric methods, retrieval-augmented generation performs best, while in-context learning degrades beyond two examples due to context saturation. Supervised fine-tuning achieves the largest improvement by internalizing Solidity-specific constraints into model parameters. Overall, our study provides a comprehensive benchmark for repository-level Solidity code generation and shows that high-quality domain data combined with supervised fine-tuning is the most effective strategy for improving the reliability of LLM-generated smart contracts.