CoDe-R: Refining Decompiler Output with LLMs via Rationale Guidance and Adaptive Inference

CoDe-R: Refining Decompiler Output with LLMs via Rationale Guidance and Adaptive Inference explores CoDe-R refines decompiler output with LLMs using rationale guidance and adaptive inference, achieving state-of-the-art re-executability for lightweight models.. Commercial viability score: 8/10 in Decompilation.