一作ACL 2026Poster· Natural Language Processing
TRACE : Evaluating Execution Efficiency of LLM -Based Code Translation
Zhihao Gong · Zeyu Sun · Dong Huang · Qingyuan Liang · Jie M. Zhang · Dan Hao
摘要
While Large Language Models (LLMs) have substantially improved the functional correctness of code translation, the critical dimension of execution efficiency remains overlooked. We present Trace , the first benchmark to explicitly assess efficiency in LLM-translated code. Trace includes 1,000 eff...