作者位次 #5/10ACL 2026Poster· Natural Language Processing
Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation
Le Chen · Nuo Xu · Winson Chen · Bin Lei · Pei-Hung Lin · Dunzhi Zhou · Rajeev Thakur · Caiwen Ding · Ali Jannesari · Chunhua Liao
摘要
Large language models (LLMs) have shown remarkable capabilities in code translation, yet their performance deteriorates in low-resource programming domains such as Fortran and emerging frameworks like CUDA, where high-quality parallel data are scarce. We present an automated dataset generation pi...