Related papers: Repairing Regex Vulnerabilities via Localization-G…

The existing deep learning (DL)-based automated program repair (APR) models are limited in fixing general software defects. % We present {\tool}, a DL-based approach that supports fixing for the general bugs that require dependent changes…

Locally repairable codes (LRCs) are error correcting codes used in distributed data storage. A traditional approach is to look for codes which simultaneously maximize error tolerance and minimize storage space consumption. However, this…

We study the generalization abilities of language models when translating natural language into formal specifications with complex semantics. In particular, we fine-tune language models on three datasets consisting of English sentences and…

In the domain of code generation, self-debugging is crucial. It allows LLMs to refine their generated code based on execution feedback. This is particularly important because generating correct solutions in one attempt proves challenging…

In software development, the predominant emphasis on functionality often supersedes security concerns, a trend gaining momentum with AI-driven automation tools like GitHub Copilot. These tools significantly improve developers' efficiency in…

Autonomous agents based on Large Language Models (LLMs) are increasingly being utilized in complex software systems. However, reliability remains a significant challenge due to unpredictable failures such as hallucinations, execution…

The advances of deep learning (DL) have paved the way for automatic software vulnerability repair approaches, which effectively learn the mapping from the vulnerable code to the fixed code. Nevertheless, existing DL-based vulnerability…

Code repair is a fundamental task in software development, facilitating efficient bug resolution and software maintenance. Although large language models (LLMs) have demonstrated considerable potential in automated code repair, their…

Regular expressions (regexes) are a powerful mechanism for solving string-matching problems. They are supported by all modern programming languages, and have been estimated to appear in more than a third of Python and JavaScript projects.…

Although large language models (LLMs) achieve effective safety alignment at the time of release, they still face various safety challenges. A key issue is that fine-tuning often compromises the safety alignment of LLMs. To address this…

Large language models (LLMs) have achieved decent results on automated program repair (APR). However, the next token prediction training objective of decoder-only LLMs (e.g., GPT-4) is misaligned with the masked span prediction objective of…

Large Language Models (LLMs) have shown strong capabilities in code generation and comprehension, yet their application to complex software engineering tasks often suffers from low precision and limited interpretability. We present Repeton,…

LLM-based automated program repair methods have attracted significant attention for their state-of-the-art performance. However, they were primarily evaluated on a few well known datasets like Defects4J, raising questions about their…

In distributed storage systems, locally repairable codes (LRCs) are introduced to realize low disk I/O and repair cost. In order to tolerate multiple node failures, the LRCs with \emph{$(r, \delta)$-locality} are further proposed. Since hot…

Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms…

Driven by the advancements of Large Language Models (LLMs), LLM-powered agents are making significant improvements in software engineering tasks, yet struggle with complex, repository-level issue resolution. Existing agent-based methods…

Large Language Models (LLMs) exhibit strong general language capabilities. However, fine-tuning these models on domain-specific tasks often leads to catastrophic forgetting, where the model overwrites or loses essential knowledge acquired…

Large Language Models (LLMs) have enabled intelligent agents that autonomously interact with environments and invoke external tools. Recently, agent-based software repair has drawn wide attention, as repair agents can localize bugs,…

The rise of instruction-tuned Large Language Models (LLMs) marks a significant advancement in artificial intelligence (AI) (tailored to respond to specific prompts). Despite their popularity, applying such models to debug security…

The increasing prevalence of software bugs has made automated program repair (APR) a key research focus. Large language models (LLMs) offer new opportunities for APR, but existing studies mostly rely on smaller, earlier-generation models…