Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Hellendoorn, Vincent J."'
Language models have improved by orders of magnitude with the recent emergence of Transformer-based Large Language Models (LLMs). LLMs have demonstrated their ability to generate natural code that is highly similar to code written by professional dev
Externí odkaz:
http://arxiv.org/abs/2404.15236
Pretrained models of code, such as CodeBERT and CodeT5, have become popular choices for code understanding and generation tasks. Such models tend to be large and require commensurate volumes of training data, which are rarely available for downstream
Externí odkaz:
http://arxiv.org/abs/2311.00931
Fault Localization (FL) aims to automatically localize buggy lines of code, a key first step in many manual and automatic debugging tasks. Previous FL techniques assume the provision of input tests, and often require extensive program analysis, progr
Externí odkaz:
http://arxiv.org/abs/2310.01726
Testing is an integral part of the software development process. Yet, writing tests is time-consuming and therefore often neglected. Classical test generation tools such as EvoSuite generate behavioral test suites by optimizing for coverage, but tend
Externí odkaz:
http://arxiv.org/abs/2310.01602
Large pre-trained neural language models have brought immense progress to both NLP and software engineering. Models in OpenAI's GPT series now dwarf Google's BERT and Meta's RoBERTa, which previously set new benchmarks on a wide range of NLP applicat
Externí odkaz:
http://arxiv.org/abs/2306.03268
Low-code programming allows citizen developers to create programs with minimal coding effort, typically via visual (e.g. drag-and-drop) interfaces. In parallel, recent AI-powered tools such as Copilot and ChatGPT generate programs from natural langua
Externí odkaz:
http://arxiv.org/abs/2305.20015
In text generation, models that generate text from scratch one token at a time are currently the dominant paradigm. Despite being performant, these models lack the ability to revise existing text, which limits their usability in many practical scenar
Externí odkaz:
http://arxiv.org/abs/2210.16886
A central function of code review is to increase understanding; helping reviewers understand a code change aids in knowledge transfer and finding bugs. Comments in code largely serve a similar purpose, helping future readers understand the program. I
Externí odkaz:
http://arxiv.org/abs/2204.00107
Large language models (LMs) of code have recently shown tremendous promise in completing code and synthesizing code from natural language descriptions. However, the current state-of-the-art code LMs (e.g., Codex (Chen et al., 2021)) are not publicly
Externí odkaz:
http://arxiv.org/abs/2202.13169
Structural locality is a ubiquitous feature of real-world datasets, wherein data points are organized into local hierarchies. Some examples include topical clusters in text or project hierarchies in source code repositories. In this paper, we explore
Externí odkaz:
http://arxiv.org/abs/2110.02870