Translation Tag Team: Formal Rules and LLMs Translate More Macros Together than Apart
Source
Brent Pappas, Joseph Zalusky, Zachary Burkett, Paul Gazzillo
Author
Brent Pappas, Joseph Zalusky, Zachary Burkett, Paul Gazzillo
Date
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
Why it matters
The measured finding that running the formal translator first and falling back to a model on the remainder beats either alone is a directly applicable strategy for LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition →-assisted migration work.
articleCodeTransBenchmark: Evaluating LLM-based Code Translation and Repair Across Programming LanguagesVera Kowalczuk, Oliver Wei{\ss}l, Severin Kacianka, Andrea Stocco
articleAn Extensive Empirical Study on Code Translation TechniqueRuihang Fan, Jiajun Jiang, Xinpeng Wang, Jiateng Fu, Fengjie Li, Jiasi Shen
articleFrom C to Idiomatic Rust: A Ship-of-Theseus Agentic TranslationVasily A. Sartakov