Assessing Code Understanding in LLMs

We present an empirical evaluation of Large Language Models in code understanding associated with non-trivial, semantic-preserving program transformations such as copy propagation or constant folding. Our findings show that LLMs fail to judge semantic equivalence in approximately 41% of cases when no context is provided and in 29% when given a simple generic context. To improve accuracy, we advocate integrating LLMs with code-optimization tools to enhance training and facilitate more robust program understanding.