A survey on large language models for software engineering

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

Enchanting program specification synthesis by large language models using static analysis and program verification

C Wen, J Cao, J Su, Z Xu, S Qin, M He, H Li… - … on Computer Aided …, 2024 - Springer
Formal verification provides a rigorous and systematic approach to ensure the correctness
and reliability of software systems. Yet, constructing specifications for the full proof relies on …

Exploiting privacy vulnerabilities in open source llms using maliciously crafted prompts

G Choquet, A Aizier, G Bernollin - 2024 - researchsquare.com
The proliferation of AI technologies has brought to the forefront concerns regarding the
privacy and security of user data, particularly with the increasing deployment of powerful …

Interleaving static analysis and llm prompting

PJ Chapman, C Rubio-González… - … on the State Of the Art in …, 2024 - dl.acm.org
This paper presents a new approach for using Large Language Models (LLMs) to improve
static program analysis. Specifically, during program analysis, we interleave calls to the …

When Threads Meet Interrupts: Effective Static Detection of {Interrupt-Based} Deadlocks in Linux

C Ye, Y Cai, C Zhang - 33rd USENIX Security Symposium (USENIX …, 2024 - usenix.org
Deadlocking is an unresponsive state of software that arises when threads hold locks while
trying to acquire other locks that are already held by other threads, resulting in a circular lock …

Evaluating large language models for software testing

Y Li, P Liu, H Wang, J Chu, WE Wong - Computer Standards & Interfaces, 2025 - Elsevier
Large language models (LLMs) have demonstrated significant prowess in code analysis
and natural language processing, making them highly valuable for software testing. This …

A Comprehensive Review of Static Memory Analysis

T Akinyemi, E Solomon, A Woubie, K Lippert - IEEE Access, 2024 - ieeexplore.ieee.org
This review aims to evaluate and compare various static analysis tools across multiple
programming languages for memory management. The tools and techniques under scrutiny …

The Current Challenges of Software Engineering in the Era of Large Language Models

C Gao, X Hu, S Gao, X **a, Z ** - ACM Transactions on Software …, 2024 - dl.acm.org
With the advent of large language models (LLMs) in the artificial intelligence (AI) area, the
field of software engineering (SE) has also witnessed a paradigm shift. These models, by …

CFStra: Enhancing Configurable Program Analysis Through LLM-Driven Strategy Selection Based on Code Features

J Su, L Deng, C Wen, S Qin, C Tian - International Symposium on …, 2024 - Springer
Abstract Configurable Program Analysis (CPA) allows users to customize program analysis
based on their preferences. However, current program verification tools like Cpachecker …

Utilizing Precise and Complete Code Context to Guide LLM in Automatic False Positive Mitigation

J Chen, H **ang, L Li, Y Zhang, B Ding, Q Li - arxiv preprint arxiv …, 2024 - arxiv.org
Static Application Security Testing (SAST) tools are crucial for early bug detection and code
quality but often generate false positives that slow development. Automating false positive …