Humaneval-Decompile Benchmark

The Humaneval-Decompile Benchmark is a dataset used to evaluate the effectiveness of decompilation methods by assessing their ability to accurately reconstruct high-level programming languages from compiled low-level code.

Papers using Humaneval-Decompile Benchmark (3)

CoDe-R: Refining Decompiler Output with LLMs via Rationale Guidance and Adaptive Inference2026HELIOS: Hierarchical Graph Abstraction for Structure-Aware LLM Decompilation2026ReF Decompile: Relabeling and Function Call Enhanced Decompile2025