Papers › LLM4Decompile: Decompiling Binary Code with Large Language Models

LLM4Decompile: Decompiling Binary Code with Large Language Models

8 Mar 2024arXiv:2403.05286archive 2025-07-28

Hanzhuo Tan, Qi Luo, Jing Li, Yuqun Zhang

Decompilation aims to convert binary code to high-level source code, but traditional tools like Ghidra often produce results that are difficult to read and execute. Motivated by the advancements in Large Language Models (LLMs), we propose LLM4Decompile, the first and largest open-source LLM series (1.3B to 33B) trained to decompile binary code. We optimize the LLM training process and introduce the LLM4Decompile-End models to decompile binary directly. The resulting models significantly outperform GPT-4o and Ghidra on the HumanEval and ExeBench benchmarks by over 100% in terms of re-executability rate. Additionally, we improve the standard refinement approach to fine-tune the LLM4Decompile-Ref models, enabling them to effectively refine the decompiled code from Ghidra and achieve a further 16.2% improvement over the LLM4Decompile-End. LLM4Decompile demonstrates the potential of LLMs to revolutionize binary code decompilation, delivering remarkable improvements in readability and executability while complementing conventional tools for optimal results. Our code, dataset, and models are released at https://github.com/albertan017/LLM4Decompile

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 13 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 9 ran (4 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

albertan017/LLM4Decompile officialmentioned in papermentioned on GitHubpytorchMITSyntology: 13 samples, 9 ran (5 instrument-failed) · 4 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
5ran · our draft was wrong
3ran
4unverified

Licence: 1 of the 13 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from albertan017/LLM4Decompile. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

albertan017/LLM4Decompile official repository 13 samples, 9 ran (5 instrument-failed) · 4 unverified
activate_neftune train/colossalai_llm4decompile/colossal_llama/utils/neftune_patch.py ran MIT (permissive) · 5fcfb774c79b9b7d · report fixture: signature model:callable/0/?, neftune_noise_alpha:float/0/float · returned tuple · level recorded 2026-09-24
build_instruction_prompt in 5 papers train/finetune.py ran · our draft was wrong fingerprinted MIT (permissive) · 4fd02bfccdbf12b1 · report fixture: signature instruction:str/0/str · returned str · level recorded 2026-09-24
evaluate_func evaluation/run_evaluation_llm4decompile.py ran · honoured contract MIT (permissive) · 9a27b34db2c2024d · report fixture: signature params:dict/0/? · returned tuple · level recorded 2026-09-24
get_prompt_template in 12 papers train/colossalai_llm4decompile/colossal_llama/utils/stream_chat_patch.py ran MIT (permissive) · fea66d04230199f0 · report fixture: signature input_query:str/0/str, history:list/1/dict, roles:list/1/str · returned str · level recorded 2026-09-24
load_json in 344 papers train/colossalai_llm4decompile/colossal_llama/utils/ckpt_io.py ran · our draft was wrong MIT (permissive) · edd6dea17a852638 · report fixture: signature file_path:str/0/str · returned dict · level recorded 2026-09-24
load_tokenized_dataset train/colossalai_llm4decompile/colossal_llama/dataset/loader.py ran · our draft was wrong MIT (permissive) · ef17eb15727ac3ea · report fixture: signature dataset_paths:list/1/str, mode:str/0/str · returned ConcatDataset · level recorded 2026-09-24
neftune_post_forward_hook train/colossalai_llm4decompile/colossal_llama/utils/neftune_patch.py ran MIT (permissive) · c438348a5d3162c5 · report fixture: signature module:callable/0/?, input:Tensor/2/int, output:Tensor/3/float · returned Tensor · level recorded 2026-09-24
preprocess in 284 papers
census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket
train/finetune.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 51c01dd0d033f660 · report fixture: signature sources:list/1/str, targets:list/1/str, tokenizer:callable/0/? · returned dict · level recorded 2026-09-24
unwrap in 16 papers train/colossalai_llm4decompile/colossal_llama/utils/neftune_patch.py ran · our draft was wrong MIT (permissive) · 17ffab2bd6e83923 · report fixture: signature model:callable/0/? · returned SimpleModel · level recorded 2026-09-24
decompile_pass_rate evaluation/run_evaluation_llm4decompile.py unverified MIT (permissive) · f9d7560dd23456b3 · report
decompile_pass_rate evaluation/run_evaluation_llm4decompile_vllm.py unverified MIT (permissive) · b830c89787dddfa0 · report
evaluate_func evaluation/run_evaluation_llm4decompile_singleGPU.py unverified MIT (permissive) · c00605edd20c1e97 · report
train_tokenize_function train/finetune.py unverified MIT (permissive) · 1eb7810bff597f27 · report

Tasks

HumanEval

Datasets

Introduced by this paper, per the archive.

decompile-ghidra-100k

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutGPT-4Label SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections