Integrating Rules and Semantics for LLM-Based C-to-Rust Translation

TL;DR

This paper introduces IRENE, a novel LLM-based framework that combines rules and semantics to improve the accuracy and safety of translating legacy C code into Rust, addressing limitations of previous methods.

Contribution

IRENE integrates rule-based retrieval, structured summarization, and error-driven refinement to enhance C-to-Rust translation with LLMs, improving semantic consistency and rule adherence.

Findings

Improved translation accuracy on benchmark datasets

Enhanced safety by reducing unsafe code blocks

Effective handling of Rust rules and semantics

Abstract

Automated translation of legacy C code into Rust aims to ensure memory safety while reducing the burden of manual migration. Early approaches in code translation rely on static rule-based methods, but they suffer from limited coverage due to dependence on predefined rule patterns. Recent works regard the task as a sequence-to-sequence problem by leveraging large language models (LLMs). Although these LLM-based methods are capable of reducing unsafe code blocks, the translated code often exhibits issues in following Rust rules and maintaining semantic consistency. On one hand, existing methods adopt a direct prompting strategy to translate the C code, which struggles to accommodate the syntactic rules between C and Rust. On the other hand, this strategy makes it difficult for LLMs to accurately capture the semantics of complex code. To address these challenges, we propose IRENE, an LLM-based framework that Integrates RulEs aNd sEmantics to enhance translation. IRENE consists of three modules: 1) a rule-augmented retrieval module that selects relevant translation examples based on rules generated from a static analyzer developed by us, thereby improving the handling of Rust rules; 2) a structured summarization module that produces a structured summary for guiding LLMs to enhance the semantic understanding of C code; 3) an error-driven translation module that leverages compiler diagnostics to iteratively refine translations. We evaluate IRENE on two datasets (xCodeEval, a public dataset, and HW-Bench, an industrial dataset provided by Huawei) and eight LLMs, focusing on translation accuracy and safety.