[PDF][PDF] Unifying the perspectives of nlp and software engineering: A survey on language models for code

Z Zhang, C Chen, B Liu, C Liao, Z Gong… - arXiv preprint arXiv …, 2023 - simg.baai.ac.cn
In this work we systematically review the recent advancements in code processing with
language models, covering 50+ models, 30+ evaluation tasks, 170+ datasets, and 700 …

Generative Artificial Intelligence for Software Security Analysis: Fundamentals, Applications, and Challenges

A Ding, G Li, X Yi, X Lin, J Li, C Zhang - IEEE Software, 2024 - ieeexplore.ieee.org
Generative AI for Software Security Analysis: Fundamentals, Applications, and Challenges
Page 1 46 IEEE SOFTWARE | PUBLISHED BY THE IEEE COMPUTER SOCIETY 0740-7459/24©2024IEEE …

A survey on large language models for software engineering

Q Zhang, C Fang, Y Xie, Y Zhang, Y Yang… - arXiv preprint arXiv …, 2023 - arxiv.org
Software Engineering (SE) is the systematic design, development, and maintenance of
software applications, underpinning the digital infrastructure of our modern mainworld. Very …

How Far Are We From AGI

T Feng, C Jin, J Liu, K Zhu, H Tu, Z Cheng… - arXiv preprint arXiv …, 2024 - arxiv.org
The evolution of artificial intelligence (AI) has profoundly impacted human society, driving
significant advancements in multiple sectors. Yet, the escalating demands on AI have …

LLM4Decompile: Decompiling Binary Code with Large Language Models

H Tan, Q Luo, J Li, Y Zhang - arXiv preprint arXiv:2403.05286, 2024 - arxiv.org
Decompilation aims to restore compiled code to human-readable source code, but struggles
with details like names and structure. Large language models (LLMs) show promise for …

Optimizing Decompiler Output by Eliminating Redundant Data Flow in Self-Recursive Inlining

R Zhang, Y Cao, R Liang, P Hu… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
Decompilation, which aims to lift a binary to a high-level language such as C, is one of the
most common approaches software security analysts use for analyzing binary code …

Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs

Z Ji, D Wu, P Ma, Z Li, S Wang - arXiv preprint arXiv:2404.17833, 2024 - arxiv.org
Agents based on large language models (LLMs) have demonstrated effectiveness in solving
a wide range of tasks by integrating LLMs with key modules such as planning, memory, and …

Self-Constructed Context Decompilation with Fined-grained Alignment Enhancement

Y Feng, D Teng, Y Xu, H Mu, X Xu, L Qin, Q Zhu… - arXiv preprint arXiv …, 2024 - arxiv.org
Decompilation transforms compiled code back into a high-level programming language for
analysis when source code is unavailable. Previous work has primarily focused on …

Exploring the Efficacy of Large Language Models (GPT-4) in Binary Reverse Engineering

S Pordanesh, B Tan - arXiv preprint arXiv:2406.06637, 2024 - arxiv.org
This study investigates the capabilities of Large Language Models (LLMs), specifically GPT-
4, in the context of Binary Reverse Engineering (RE). Employing a structured experimental …

MAD: Move AI Decompiler to Improve Transparency and Auditability on Non-Open-Source Blockchain Smart Contract

E Chen, X Tang, Z Xiao, C Li, S Li, W Tingguan… - arXiv preprint arXiv …, 2024 - arxiv.org
Web3 aims to enhance user control over data and assets, but this vision is challenged by
non-transparent, scam-prone applications and vulnerable smart contracts. While code audits …