MMODELYST
Papers/Beyond BLEU: A Semantic Evaluation Method for Code Translation
PAP

Beyond BLEU: A Semantic Evaluation Method for Code Translation

May 6, 2026

arXiv
Abstract

Code translation is one of the core capabilities of LLMs. However, evaluating the correctness of translations remains difficult, as commonly used metrics such as BLEU measure only syntactic similarity, disregarding program semantics. We propose a novel evaluation methodology for code translation tasks, emphasizing semantic equivalence over surface-level string similarity. Our approach applies established compiler testing methodology to a new domain, allowing the assessment of an LLM fine-tuned for binary lifting tasks (i.e. decompiling binaries to higher-level representations). We introduce a semantic correctness score, defined as the proportion of translations that produce correct execution outcomes, and demonstrate its application by evaluating LLM-based and heuristic decompilers. Our findings show that LLM-based approaches significantly outperform heuristic ones, while BLEU scores show negligible correlation with semantic correctness (r = -0.127 to 0.354), demonstrating that syntactic metrics fail to predict functional accuracy.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Julius Näumann, Sven Keidel, Amir Molzam Sharifloo, Mira Mezini
Your notes (browser-local)
saved
arXiv:2605.05282