微调Qwen3-27B实现C到Rust代码翻译：预训练、调试感知监督微调与任务特定监督微调的三阶段课程

中文摘要 AI 辅助

将C代码转换为安全、符合习惯用法的Rust代码是一项长期存在的软件工程目标，因为这可以在保留遗留系统功能行为的同时，消除整类内存安全漏洞。大语言模型（LLM）在该任务上展现出潜力，但直接应用时通常表现不佳，因为通用预训练很少强调符合习惯用法的Rust生成、跨语言语义等价性，或推理及修复编译器/运行时反馈的能力。本报告描述了应用于Qwen3-27B的三阶段微调课程，旨在逐步将模型专门化以完成C到Rust（C2Rust）翻译任务：（1）在以Rust为中心的语料库上进行持续预训练，以增强模型对符合习惯用法的Rust语法及标准库使用的先验知识；（2）在microsoft/Verus_Training_Data数据集上进行监督微调（SFT），以灌输Rust代码的调试与自我修复行为；（3）在源自LeetCode问题的配对C/Rust解决方案上进行任务特定SFT，以教授直接语义翻译。我们使用SACTOR的智能体、静态分析引导验证框架评估所得模型，该框架执行结构感知的两阶段（非习惯用法到习惯用法）翻译，并进行基于外部函数接口（FFI）的端到端（E2E）测试。我们报告了成功率、习惯用法性（Clippy lint数量、不安全代码占比）及失败模式分析，并在相同框架下将我们的微调模型与基线Qwen3-27B及其他LLM进行比较。

英文摘要

Translating C code into safe, idiomatic Rust is a longstanding software-engineering goal because it can eliminate entire classes of memory-safety vulnerabilities while preserving the functional behavior of legacy systems. Large language models (LLMs) have shown promise for this task but typically underperform when applied off-the-shelf, since general-purpose pretraining rarely emphasizes idiomatic Rust generation, cross-language semantic equivalence, or the ability to reason about and repair compiler/runtime feedback. In this report we describe a three-stage fine-tuning curriculum applied to Qwen3-27B that is designed to progressively specialize the model for the C-to-Rust (C2Rust) translation task: (1) continued pretraining on Rust-centric corpora to strengthen the model's prior over idiomatic Rust syntax and standard-library usage; (2) supervised fine-tuning (SFT) on the microsoft/Verus_Training_Data dataset to instill debugging and self-repair behavior over Rust code; and (3) task-specific SFT on paired C/Rust solutions derived from LeetCode problems to teach direct semantic translation. We evaluate the resulting model using the agentic, static-analysis-guided verification framework of SACTOR, which performs structure-aware, two-phase (unidiomatic to idiomatic) translation with foreign-function-interface (FFI)-based end-to-end (E2E) testing. We report success rate, idiomaticity (Clippy lint counts, unsafe-code fraction), and failure-mode analyses, and compare our fine-tuned model against baseline Qwen3-27B and other LLMs evaluated under the same framework.

发表机构

• Northeastern University（东北大学）
• EmbodyX Inc（EmbodyX公司）
• Aibao LLC（Aibao有限责任公司）

机构由 AI 辅助整理，请以论文原文为准。