LLMs as Idiomatic Decompilers: Recovering High-Level Code from x86-64 Assembly for Dart
arXiv:2604.02278v1 Announce Type: new Abstract: Translating machine code into human-readable high-level languages is an open research problem in reverse engineering. Despite recent advancements in LLM-based decompilation to C, modern languages like Dart and Swift are unexplored. In this paper, we study the use of small specialized LLMs as an idiomatic decompiler for such languages. Additionally, we investigate the augmentation of training data using synthetic same-language examples, and compare it against adding human-written examples using related-language (Swift -> Dart). We apply CODEBLEU to evaluate the decompiled code readability and compile@k to measure the syntax correctness. Our experimental results show that on a 73-function Dart test dataset (representing diverse complexity level
View PDF HTML (experimental)
Abstract:Translating machine code into human-readable high-level languages is an open research problem in reverse engineering. Despite recent advancements in LLM-based decompilation to C, modern languages like Dart and Swift are unexplored. In this paper, we study the use of small specialized LLMs as an idiomatic decompiler for such languages. Additionally, we investigate the augmentation of training data using synthetic same-language examples, and compare it against adding human-written examples using related-language (Swift -> Dart). We apply CODEBLEU to evaluate the decompiled code readability and compile@k to measure the syntax correctness. Our experimental results show that on a 73-function Dart test dataset (representing diverse complexity levels), our 4B specialized model achieves 71.3 CODEBLEU (95% CI 65.5-77.1), approximately comparable to a ~480B code model (73.1; 67.4-78.8). On a subset of 34 natural Dart functions, it reaches compile@k5 = 79.4% (Wilson 95% CI 63.2-89.7), vs. 64.7% (47.9-78.5) for the base model; the difference is suggestive but not statistically significant at 0.05. Our results indicate that adding Swift training data helps at 8B but not at 4B, suggesting a capacity threshold for effective cross-lingual transfer. Our experimental results show that small specialized models can generate readable, idiomatic Dart with meaningful identifiers while using minimal compute.
Comments: 5 pages, 1 figure, 3 tables. Accepted at SANER 2026 ERA Track
Subjects:
Software Engineering (cs.SE)
ACM classes: D.3.4; I.2.7; D.2.7
Cite as: arXiv:2604.02278 [cs.SE]
(or arXiv:2604.02278v1 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2604.02278
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Raafat Abualazm [view email] [v1] Thu, 2 Apr 2026 17:12:36 UTC (27 KB)
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
modeltrainingannounce
Semantic matching in graph space without matrix computation and hallucinations and no GPU
Hello AI community,For the past few months, I’ve been rethinking how AI should process language and logic. Instead of relying on heavy matrix multiplications (Attention mechanisms) to statistically guess the next word inside an unexplainable black box, I asked a different question: What if concepts existed in a physical, multi-dimensional graph space where logic is visually traceable?I am excited to share our experimental architecture. To be absolutely clear: this is not a GraphRAG system built on top of an existing LLM. This is a standalone Native Graph Cognitive Engine.The Core Philosophy:Zero-Black-Box (Total Explainability): Modern LLMs are black boxes; you never truly know why they chose a specific token. Our engine is a “glass brain.” Every logical leap and every generated sentence i
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Research Papers
VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors
Vision Language Models struggle with fine-grained visual perception tasks due to their language-centric training approach, performing poorly on unnamed visual entities despite having relevant information in their representations. (1 upvotes on HuggingFace)
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!