ICL4Decomp applies in-context learning to guide LLMs in generating re-executable decompiled code from binaries, reporting roughly 40% higher re-executability than prior methods across datasets and optimization levels.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SE 2verdicts
UNVERDICTED 2representative citing papers
The sum of verifier warnings adds no useful predictive power for code comprehensibility beyond syntactic and developer features.
citing papers explorer
-
Context-Guided Decompilation: A Step Towards Re-executability
ICL4Decomp applies in-context learning to guide LLMs in generating re-executable decompiled code from binaries, reporting roughly 40% higher re-executability than prior methods across datasets and optimization levels.
-
Verifier Warnings Do Not Improve Comprehensibility Prediction
The sum of verifier warnings adds no useful predictive power for code comprehensibility beyond syntactic and developer features.