Related papers: Issue Retrieval and Verification Enhanced Suppleme…

Method-level comments are critical for improving code comprehension and supporting software maintenance. With advancements in large language models (LLMs), automated comment generation has become a major research focus. However, existing…

Previous studies have shown that high-quality code comments assist developers in program comprehension and maintenance tasks. However, the semi-structured nature of comments, unclear conventions for writing good comments, and the lack of…

Code comment generation aims to generate high-quality comments from source code automatically and has been studied for years. Recent studies proposed to integrate information retrieval techniques with neural generation models to tackle this…

Retrieval-augmented generation (RAG) has become integral to large language models (LLMs), particularly for conversational AI systems where user questions may reference knowledge beyond the LLMs' training cutoff. However, many natural user…

This paper describes an approach to improve code comments along different quality axes by rewriting those comments with customized Artificial Intelligence (AI)-based tools. We conduct an empirical study followed by grounded theory…

Identifying and addressing security issues during the early phase of the development lifecycle is critical for mitigating the long-term negative impacts on software systems. Code review serves as an effective practice that enables…

Prompting-based large language models (LLMs) are surprisingly powerful at generating natural language reasoning steps or Chains-of-Thoughts (CoT) for multi-step question answering (QA). They struggle, however, when the necessary knowledge…

Code comment generation aims at generating natural language descriptions for a code snippet to facilitate developers' program comprehension activities. Despite being studied for a long time, a bottleneck for existing approaches is that…

Large language model (LLM)-powered code review automation tools have been introduced to generate code review comments. However, not all generated comments will drive code changes. Understanding what types of generated review comments are…

We conduct a large-scale empirical user study in a live setup to evaluate the acceptance of LLM-generated comments and their impact on the review process. This user study was performed in two organizations, Mozilla (which has its codebase…

Large Language models (LLMs) have shown strong capabilities in code review automation, such as review comment generation, yet they suffer from hallucinations -- where the generated review comments are ungrounded in the actual code -- poses…

Pre-trained code models rely heavily on high-quality pre-training data, particularly human-written reference comments that bridge code and natural language. However, these comments often become outdated as software evolves, degrading model…

Large Language Models are increasingly used in software engineering, but both code generation and its evaluation remain predominantly English-centric. This leaves a major gap in our understanding of how well current tools support…

Issue-commit linking, which connects issues with commits that fix them, is crucial for software maintenance. Existing approaches have shown promise in automatically recovering these links. Evaluations of these techniques assess their…

While large language models (LLMs) have shown remarkable capabilities to generate coherent text, they suffer from the issue of hallucinations -- factually inaccurate statements. Among numerous approaches to tackle hallucinations, especially…

Large Language Models (LLMs) are increasingly used to generate summaries of software bug reports, including sections such as Steps-to-Reproduce (S2R), Actual Behavior (AB), and Expected Behavior (EB). However, these models frequently…

Large Language Models (LLMs) are widely used to support software developers in tasks such as code generation, optimization, and documentation. However, their ability to improve existing programming answers in a human-like manner remains…

Large language models are limited by challenges in factuality and hallucinations to be directly employed off-the-shelf for judging the veracity of news articles, where factual accuracy is paramount. In this work, we propose DELL that…

Query expansion is a long-standing technique to mitigate vocabulary mismatch in ad hoc Information Retrieval. Pseudo-relevance feedback methods, such as RM3, estimate an expanded query model from the top-ranked documents, but remain…

Aim. There are 10s of thousands of code review comments each week at Meta. We developed Metamate for Code Review (MetaMateCR) that provides AI-assisted fixes for reviewer comments in production at scale. Method. We developed an internal…