This paper provides a survey of the emerging area of Large Language Models (LLMs) for Software Engineering (SE). It also sets out open research challenges for the application of …
The main challenges are discussed together with the lessons learned from past and ongoing research along the development cycle of machine learning systems. This will be …
B Roziere, MA Lachaux… - Advances in neural …, 2020 - proceedings.neurips.cc
A transcompiler, also known as source-to-source translator, is a system that converts source code from a high-level programming language (such as C++ or Python) to another …
Y Tian, K Pei, S Jana, B Ray - … of the 40th international conference on …, 2018 - dl.acm.org
Recent advances in Deep Neural Networks (DNNs) have led to the development of DNN- driven autonomous cars that, using sensors like camera, LiDAR, etc., can drive without any …
Among the many software testing techniques available today, fuzzing has remained highly popular due to its conceptual simplicity, its low barrier to deployment, and its vast amount of …
Mutation testing realizes the idea of using artificial defects to support testing activities. Mutation is typically used as a way to evaluate the adequacy of test suites, to guide the …
A test oracle determines whether a test execution reveals a fault, often by comparing the observed program output to the expected output. This is not always practical, for example …
Identifying invariants is an important program analysis task with applications towards program understanding, bug finding, vulnerability analysis, and formal verification. Existing …
• There are IDEs for KeY, including an Eclipse extension, that make it easy to keep track of proof obligations in larger projects [Hentschel et al., 2014c].• A stripped down version of …