REBench is a new benchmark that consolidates existing datasets into a large collection of binaries with knowledge-base-driven ground truth to enable fair LLM evaluation on stripped-binary type and name recovery.
Lmpa: Improving decompilation by synergy of large lan- guage model and program analysis
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Rationale-guided fine-tuning plus dual-path adaptive inference lifts a 1.3B decompiler refiner to 50% average re-executability, a new lightweight SOTA on HumanEval-Decompile.
citing papers explorer
-
REBENCH: A Procedural, Fair-by-Construction Benchmark for LLMs on Stripped-Binary Types and Names (Extended Version)
REBench is a new benchmark that consolidates existing datasets into a large collection of binaries with knowledge-base-driven ground truth to enable fair LLM evaluation on stripped-binary type and name recovery.
-
CoDe-R: Refining Decompiler Output with LLMs via Rationale Guidance and Adaptive Inference
Rationale-guided fine-tuning plus dual-path adaptive inference lifts a 1.3B decompiler refiner to 50% average re-executability, a new lightweight SOTA on HumanEval-Decompile.