38 citations · 103 across the 14 of their papers we have counts for
14 papers
SOSecure: Safer Code Generation with RAG and StackOverflow Discussions
Manisha Mukherjee, Vincent J. Hellendoorn
Large Language Models (LLMs) are widely used for automated code generation. Their reliance on infrequently updated pretraining data leaves them unaware of newly discovered vulnerab…
Revisiting Unnaturalness for Automated Program Repair in the Era of Large Language Models
Aidan Z. H. Yang, Sophia Kolak, Vincent J. Hellendoorn +2
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 n…
Learning Defect Prediction from Unrealistic Data
Kamel Alrashedy, Vincent J. Hellendoorn, Alessandro Orso
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 commensura…
Large Language Models for Test-Free Fault Localization
Aidan Z. H. Yang, Ruben Martins, Claire Le Goues +1
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 provisi…
CAT-LM: Training Language Models on Aligned Code And Tests
Nikitha Rao, Kush Jain, Uri Alon +2
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 EvoSuit…
Skill over Scale: The Case for Medium, Domain-Specific Models for SE
Manisha Mukherjee, Vincent J. Hellendoorn
Recent advancements in AI have sparked a trend in constructing large, generalist language models that handle a multitude of tasks, including many code-related ones. While these mod…
AI for Low-Code for AI
Nikitha Rao, Jason Tsay, Kiran Kate +2
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 t…
DiffusER: Discrete Diffusion via Edit-based Reconstruction
Machel Reid, Vincent J. Hellendoorn, Graham Neubig
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 revis…
Comments on Comments: Where Code Review and Documentation Meet
Nikitha Rao, Jason Tsay, Martin Hirzel +1
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 ser…
A Systematic Evaluation of Large Language Models of Code
Frank F. Xu, Uri Alon, Graham Neubig +1
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-o…
Capturing Structural Locality in Non-parametric Language Models
Frank F. Xu, Junxian He, Graham Neubig +1
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 proj…
Memorization and Generalization in Neural Code Intelligence Models
Md Rafiqul Islam Rabin, Aftab Hussain, Mohammad Amin Alipour +1
Deep Neural Networks (DNNs) are increasingly being used in software engineering and code intelligence tasks. These are powerful tools that are capable of learning highly generaliza…
Understanding Neural Code Intelligence Through Program Simplification
Md Rafiqul Islam Rabin, Vincent J. Hellendoorn, Mohammad Amin Alipour
A wide range of code intelligence (CI) tools, powered by deep neural networks, have been developed recently to improve programming productivity and perform program analysis. To rel…
Are My Invariants Valid? A Learning Approach
Vincent J. Hellendoorn, Premkumar T. Devanbu, Oleksandr Polozov +1
Ensuring that a program operates correctly is a difficult task in large, complex systems. Enshrining invariants -- desired properties of correct execution -- in code or comments ca…