@inproceedings{mcdanel-liu-2023-chatgpt,
    title = "{C}hat{GPT} as a {J}ava Decompiler",
    author = "Mcdanel, Bradley  and
      Liu, Zhanhao",
    editor = "Gehrmann, Sebastian  and
      Wang, Alex  and
      Sedoc, Jo{\~a}o  and
      Clark, Elizabeth  and
      Dhole, Kaustubh  and
      Chandu, Khyathi Raghavi  and
      Santus, Enrico  and
      Sedghamiz, Hooman",
    booktitle = "Proceedings of the Third Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.gem-1.19/",
    pages = "224--232",
    abstract = "We propose a novel approach using instruction-tuned large language models (LLMs), such as ChatGPT, to automatically decompile entire Java classes. Our method relies only on a textual representation of the Java bytecode and corresponding unit tests generated from the bytecode. While no additional domain knowledge or fine-tuning is performed, we provide a single training example of this decompilation process in the model{'}s prompt. To overcome both compilation errors and test failures, we use an iterative prompting approach. We find that ChatGPT-4 is able to generate more human-readable output than existing software-based decompilers while achieving slightly lower pass rates on unit tests. Source code and datasets are available at \url{https://github.com/BradMcDanel/gpt-java-decompiler}."
}