Abstract: Deep code models are vulnerable to adversarial attacks, making it possible for semantically identical inputs to trigger different responses. Current black-box attack methods typically ...

Retrieval-augmented generation breaks at scale because organizations treat it like an LLM feature rather than a platform ...

The purpose of this repository is to provide a few sample prompts used in order to create a simple Python GUI for the Linux desktop project. I created this repository and wrote these prompts on March ...

Abstract: Large Language Models (LLMs) are increasingly used by software engineers for code generation. However, limitations of LLMs such as irrelevant or incorrect code have highlighted the need for ...