MOS applies mixture-of-experts tuning to a 3B-parameter LLM, specializing experts per vulnerability type and reporting state-of-the-art detection and explanation quality on reentrancy, timestamp, overflow, and delegatecall tests.
Safurai-Csharp: Harnessing Synthetic Data to improve language-specific Code LLM
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper introduces Safurai-Csharp, an open-source model designed to specialize in the generation, completion, and debugging of C# code. Safurai-Csharp is built upon the novel CodeLlama 34B model and leverages the EvolInstruct technique, creating a refined and expanded dataset for its fine-tuning process. The results of its performance, a notable score of 56.33% on the Manual MultiPL-E benchmark (Zero-Shot, Pass@1), signal its high capacity to streamline developers' workflows and aid code learning. It shows promise in setting new stakes in the landscape of open-source C# LLMs and hopes to inspire more inclusive and wide-ranging development in the field of language-specific LLMs.
fields
cs.SE 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
MOS: Towards Effective Smart Contract Vulnerability Detection through Mixture-of-Experts Tuning of Large Language Models
MOS applies mixture-of-experts tuning to a 3B-parameter LLM, specializing experts per vulnerability type and reporting state-of-the-art detection and explanation quality on reentrancy, timestamp, overflow, and delegatecall tests.