Large language models for software engineering: A systematic literature review

X Hou, Y Zhao, Y Liu, Z Yang, K Wang, L Li… - ACM Transactions on …, 2024 - dl.acm.org
Large Language Models (LLMs) have significantly impacted numerous domains, including
Software Engineering (SE). Many recent publications have explored LLMs applied to …

When chatgpt meets smart contract vulnerability detection: How far are we?

C Chen, J Su, J Chen, Y Wang, T Bi, J Yu… - ACM Transactions on …, 2023 - dl.acm.org
With the development of blockchain technology, smart contracts have become an important
component of blockchain applications. Despite their crucial role, the development of smart …

Evaluating large language models in class-level code generation

X Du, M Liu, K Wang, H Wang, J Liu, Y Chen… - Proceedings of the …, 2024 - dl.acm.org
Recently, many large language models (LLMs) have been proposed, showing advanced
proficiency in code generation. Meanwhile, many efforts have been dedicated to evaluating …

Smartinv: Multimodal learning for smart contract invariant inference

SJ Wang, K Pei, J Yang - 2024 IEEE Symposium on Security and …, 2024 - computer.org
Smart contracts are software programs that enable diverse business activities on the
blockchain. Recent research has identified new classes of “machine un-auditable” bugs that …

A new approach to web application security: Utilizing gpt language models for source code inspection

Z Szabó, V Bilicki - Future Internet, 2023 - mdpi.com
Due to the proliferation of large language models (LLMs) and their widespread use in
applications such as ChatGPT, there has been a significant increase in interest in AI over the …

Large language model-powered smart contract vulnerability detection: New perspectives

S Hu, T Huang, F İlhan, SF Tekin… - 2023 5th IEEE …, 2023 - ieeexplore.ieee.org
This paper provides a systematic analysis of the opportunities, challenges, and potential
solutions of harnessing Large Language Models (LLMs) such as GPT-4 to dig out …

Resolving Crash Bugs via Large Language Models: An Empirical Study

X Du, M Liu, J Li, H Wang, X Peng, Y Lou - arxiv preprint arxiv …, 2023 - arxiv.org
Crash bugs cause unexpected program behaviors or even termination, requiring high-
priority resolution. However, manually resolving crash bugs is challenging and labor …

Beyond fidelity: Explaining vulnerability localization of learning-based detectors

B Cheng, S Zhao, K Wang, M Wang, G Bai… - ACM transactions on …, 2024 - dl.acm.org
Vulnerability detectors based on deep learning (DL) models have proven their effectiveness
in recent years. However, the shroud of opacity surrounding the decision-making process of …

Llm4fuzz: Guided fuzzing of smart contracts with large language models

C Shou, J Liu, D Lu, K Sen - arxiv preprint arxiv:2401.11108, 2024 - arxiv.org
As blockchain platforms grow exponentially, millions of lines of smart contract code are
being deployed to manage extensive digital assets. However, vulnerabilities in this mission …

LLM-CompDroid: Repairing Configuration Compatibility Bugs in Android Apps with Pre-trained Large Language Models

Z Liu, Y Tang, M Li, X **, Y Long, LF Zhang… - arxiv preprint arxiv …, 2024 - arxiv.org
XML configurations are integral to the Android development framework, particularly in the
realm of UI display. However, these configurations can introduce compatibility issues (bugs) …