Exploiting Code Symmetries for Learning Program Semantics

This paper tackles the challenge of teaching code semantics to Large Language Models (LLMs) for program analysis by incorporating code symmetries into the model architecture. We introduce a grouptheoretic framework that defines code symmetries as semantics-preserving transformations, where forming a code symmetry group enables precise and efficient reasoning of code semantics. Our solution, SYMC, develops a novel variant of self-attention that is provably equivariant to code symmetries from the permutation group defined over the program dependence graph. SYMC obtains superior performance on five program analysis tasks, outperforming stateof-the-art code models, including GPT-4, without any pre-training. Our results suggest that code LLMs that encode the code structural prior via the code symmetry group generalize better and faster.