Search Results for author: Kevin Jesse

Found 4 papers, 2 papers with code

Large Language Models and Simple, Stupid Bugs

no code implementations20 Mar 2023 Kevin Jesse, Toufique Ahmed, Premkumar T. Devanbu, Emily Morgan

We explore the consequences of the Codex generated SStuBs and propose avoidance strategies that suggest the possibility of reducing the production of known, verbatim SStubs, and increase the possibility of producing known, verbatim fixes.

Language Modelling Large Language Model

ManyTypes4TypeScript: A Comprehensive TypeScript Dataset for Sequence-Based Type Inference

1 code implementation International Conference on Mining Software Repositories 2022 Kevin Jesse, Premkumar T. Devanbu

In this paper, we present ManyTypes4TypeScript, a very large corpus for training and evaluating machine-learning models for sequence-based type inference in TypeScript.

Type prediction

Learning Type Annotation: Is Big Data Enough?

1 code implementation ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering 2021 Kevin Jesse, Premkumar T. Devanbu, Toufique Ahmed

ML approaches use different inductive biases, ranging from simple token sequences to complex graphical neural network (GNN) models capturing syntax and semantic relations.

Inductive Bias

Cannot find the paper you are looking for? You can Submit a new open access paper.