相关论文: From Query to Usable Code: An Analysis of Stack Ov…

Comparison of programming languages is a common topic of discussion among software engineers. Multiple programming languages are designed, specified, and implemented every year in order to keep up with the changing programming paradigms,…

Large language models (LLMs) and transformer-based architectures are increasingly utilized for source code analysis. As software systems grow in complexity, integrating LLMs into code analysis workflows becomes essential for enhancing…

Across all fields of academic study, experts cite their sources when sharing information. While large language models (LLMs) excel at synthesizing information, they do not provide reliable citation to sources, making it difficult to trace…

Searching code is a common task that developers perform to understand APIs, learn common code patterns, and navigate code. Currently, developers most commonly search using keywords and regular expressions that are easy to use and widely…

Spreadsheets are used to develop application software that is distributed to users. Unfortunately, the users often have the ability to change the programming statements ("source code") of the spreadsheet application. This causes a host of…

There is an increasing interest in studying natural language and computer code together, as large corpora of programming texts become readily available on the Internet. For example, StackOverflow currently has over 15 million programming…

An abstractive snippet is an originally created piece of text to summarize a web page on a search engine results page. Compared to the conventional extractive snippets, which are generated by extracting phrases and sentences verbatim from a…

Free and open source software is widely used in the creation of software systems, whereas many organisations choose to provide their systems as open source. Open source software carries licenses that determine the conditions under which the…

To translate natural language questions into executable database queries, most approaches rely on a fully annotated training set. Annotating a large dataset with queries is difficult as it requires query-language expertise. We reduce this…

The popularity of machine learning has wildly expanded in recent years. Machine learning techniques have been heatedly studied in academia and applied in the industry to create business value. However, there is a lack of guidelines for code…

When drafting question posts for Stack Overflow, developers may not accurately summarize the core problems in the question titles, which can cause these questions to not get timely help. Therefore, improving the quality of question titles…

With the advent of open source software, a veritable treasure trove of previously proprietary software development data was made available. This opened the field of empirical software engineering research to anyone in academia. Data that is…

As big data grows ubiquitous across many domains, more and more stakeholders seek to develop Machine Learning (ML) applications on their data. The success of an ML application usually depends on the close collaboration of ML experts and…

Code retrieval helps developers reuse the code snippet in the open-source projects. Given a natural language description, code retrieval aims to search for the most relevant code among a set of code. Existing state-of-the-art approaches…

In the rapidly advancing field of artificial intelligence, software development has emerged as a key area of innovation. Despite the plethora of general-purpose AI assistants available, their effectiveness diminishes in complex,…

Code example is a crucial part of good documentation. It helps the developers to understand the documentation easily and use the corresponding code unit (e.g., method) properly. However, many official documentation still lacks (good) code…

Code data has been shown to enhance the reasoning capabilities of large language models (LLMs), but it remains unclear which aspects of code are most responsible. We investigate this question with a systematic, data-centric framework. We…

Translating verbose information needs into crisp search queries is a phenomenon that is ubiquitous but hardly understood. Insights into this process could be valuable in several applications, including synthesizing large privacy-friendly…

Millions of repetitive code snippets are submitted to code repositories every day. To search from these large codebases using simple natural language queries would allow programmers to ideate, prototype, and develop easier and faster.…

Sonatype's 2023 report found that 97% of developers and security leads integrate generative Artificial Intelligence (AI), particularly Large Language Models (LLMs), into their development process. Concerns about the security implications of…