Fixing hardware security bugs with large language models

B Ahmad, S Thakur, B Tan, R Karri… - ar** enables developers to annotate types of their own choosing, offering a
flexible middle ground between no type annotations and a fully statically typed language. As …

Core: Resolving code quality issues using llms

N Wadhwa, J Pradhan, A Sonwane, SP Sahu… - Proceedings of the …, 2024 - dl.acm.org
As software projects progress, quality of code assumes paramount importance as it affects
reliability, maintainability and security of software. For this reason, static analysis tools are …

Frustrated with code quality issues? llms can help!

N Wadhwa, J Pradhan, A Sonwane, SP Sahu… - arxiv preprint arxiv …, 2023 - arxiv.org
As software projects progress, quality of code assumes paramount importance as it affects
reliability, maintainability and security of software. For this reason, static analysis tools are …

Deepcode AI fix: Fixing security vulnerabilities with large language models

B Berabi, A Gronskiy, V Raychev, G Sivanrupan… - arxiv preprint arxiv …, 2024 - arxiv.org
The automated program repair field has attracted substantial interest over the years, but
despite significant research efforts, creating a system that works well for complex semantic …

Propr: property-based automatic program repair

MP Gissurarson, L Applis, A Panichella… - Proceedings of the 44th …, 2022 - dl.acm.org
Automatic program repair (APR) regularly faces the challenge of overfitting patches---
patches that pass the test suite, but do not actually address the problems when evaluated …

Nofuneval: Funny how code lms falter on requirements beyond functional correctness

M Singhal, T Aggarwal, A Awasthi, N Natarajan… - arxiv preprint arxiv …, 2024 - arxiv.org
Existing evaluation benchmarks of language models of code (code LMs) focus almost
exclusively on whether the LMs can generate functionally-correct code. In real-world …