• Across 8 models, 3 datasets, and 12 language pairs, models trained specifically for multilingual code (like Codestral) correctly translated the majority of snippets, while most general-purpose LLMs struggled with the target language's syntax rules.
• Error analysis found translation accuracy is heavily shaped by the specific pairing of source and target languages and by what each model was trained on, not just overall model quality.
• A post-processing step built to tolerate inconsistent LLM output formatting, plus iterative repair using automated feedback on translation errors, significantly improved translation accuracy.
• The authors conclude that reliable production use of LLM code translation would require models with larger context windows than tested here.

• 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.
• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.

General-purpose LLMs frequently fail on target-language syntax during code translation, so purpose-tuned coding models are the safer default for cross-language migration work.

• articleAn Extensive Empirical Study on Code Translation TechniqueRuihang Fan, Jiajun Jiang, Xinpeng Wang, Jiateng Fu, Fengjie Li, Jiasi Shen
• articleA Study on the Impact of Natural Language Differences in Prompts on Automatic Code Generation Using LLMsHaruka Tokumasu, Masanari Kondo, Alexander Serebrenik, Dong Wang, Kei Koyanagi, Kotaro Noguchi, Naoyasu Ubayashi, Yasutaka Kamei
• articleA Systematic Evaluation of Cross-Lingual Consistency Enhancement Methods in Multilingual Language ModelsJirui Qi, Mingyang Wang, Hinrich Sch\"utze, Raquel Fern\'andez, Arianna Bisazza

Checking sign-in…

Loading comments…