Copiloting the copilots: Fusing large language models with completion engines for automated program repair
During Automated Program Repair (APR), it can be challenging to synthesize correct
patches for real-world systems in general-purpose programming languages. Recent Large …
patches for real-world systems in general-purpose programming languages. Recent Large …
How effective are neural networks for fixing security vulnerabilities
Security vulnerability repair is a difficult task that is in dire need of automation. Two groups of
techniques have shown promise:(1) large code language models (LLMs) that have been pre …
techniques have shown promise:(1) large code language models (LLMs) that have been pre …
Chatgpt: A study on its utility for ubiquitous software engineering tasks
G Sridhara, S Mazumdar - arXiv preprint arXiv:2305.16837, 2023 - arxiv.org
ChatGPT (Chat Generative Pre-trained Transformer) is a chatbot launched by OpenAI on
November 30, 2022. OpenAI's GPT-3 family of large language models serve as the …
November 30, 2022. OpenAI's GPT-3 family of large language models serve as the …
Finding the dwarf: recovering precise types from WebAssembly binaries
The increasing popularity of WebAssembly creates a demand for understanding and reverse
engineering WebAssembly binaries. Recovering high-level function types is an important …
engineering WebAssembly binaries. Recovering high-level function types is an important …
Codex hacks hackerrank: Memorization issues and a framework for code synthesis evaluation
The Codex model has demonstrated extraordinary competence in synthesizing code from
natural language problem descriptions. However, in order to reveal unknown failure modes …
natural language problem descriptions. However, in order to reveal unknown failure modes …
Is a single model enough? mucos: A multi-model ensemble learning approach for semantic code search
Recently, deep learning methods have become mainstream in code search since they do
better at capturing semantic correlations between code snippets and search queries and …
better at capturing semantic correlations between code snippets and search queries and …
DeepVulSeeker: A novel vulnerability identification framework via code graph structure and pre-training mechanism
J Wang, H Xiao, S Zhong, Y Xiao - Future Generation Computer Systems, 2023 - Elsevier
Software vulnerabilities can pose severe harms to a computing system. They can lead to
system crash, privacy leakage, or even physical damage. Correctly identifying vulnerabilities …
system crash, privacy leakage, or even physical damage. Correctly identifying vulnerabilities …
Pre-training code representation with semantic flow graph for effective bug localization
Enlightened by the big success of pre-training in natural language processing, pre-trained
models for programming languages have been widely used to promote code intelligence in …
models for programming languages have been widely used to promote code intelligence in …
The growing cost of deep learning for source code
VJ Hellendoorn, AA Sawant - Communications of the ACM, 2021 - dl.acm.org
The growing cost of deep learning for source code Page 1 JANUARY 2022 | VOL. 65 | NO. 1 |
COMMUNICATIONS OF THE ACM 31 viewpoints IMA GER YB Y OZZ DE SIGN uniquely …
COMMUNICATIONS OF THE ACM 31 viewpoints IMA GER YB Y OZZ DE SIGN uniquely …
A code centric evaluation of c/c++ vulnerability datasets for deep learning based vulnerability detection techniques
Recent years have witnessed tremendous progress in NLP-based code comprehension via
deep neural networks (DNN) learning, especially Large Language Models (LLMs). While the …
deep neural networks (DNN) learning, especially Large Language Models (LLMs). While the …