Search Results for author: Yangruibo Ding

Found 9 papers, 6 papers with code

CYCLE: Learning to Self-Refine the Code Generation

1 code implementation27 Mar 2024 Yangruibo Ding, Marcus J. Min, Gail Kaiser, Baishakhi Ray

Pre-trained code language models have achieved promising performance in code generation and improved the programming efficiency of human developers.

Vulnerability Detection with Code Language Models: How Far Are We?

no code implementations27 Mar 2024 Yangruibo Ding, Yanjun Fu, Omniyyah Ibrahim, Chawin Sitawarin, Xinyun Chen, Basel Alomair, David Wagner, Baishakhi Ray, Yizheng Chen

Evaluating code LMs on PrimeVul reveals that existing benchmarks significantly overestimate the performance of these models.

Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain

1 code implementation21 Oct 2023 Marcus J. Min, Yangruibo Ding, Luca Buratti, Saurabh Pujar, Gail Kaiser, Suman Jana, Baishakhi Ray

In this paper, we first formally define the self-consistency of Code LLMs and then design a framework, IdentityChain, which effectively and efficiently evaluates the self-consistency and conventional accuracy of a model at the same time.

Code Generation Code Summarization

CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context

no code implementations20 Dec 2022 Yangruibo Ding, Zijian Wang, Wasi Uddin Ahmad, Murali Krishna Ramanathan, Ramesh Nallapati, Parminder Bhatia, Dan Roth, Bing Xiang

While pre-trained language models (LM) for code have achieved great success in code completion, they generate code conditioned only on the contents within the file, i. e., in-file context, but ignore the rich semantics in other files within the same project, i. e., cross-file context, a critical source of information that is especially useful in modern modular software development.

Code Completion

NatGen: Generative pre-training by "Naturalizing" source code

1 code implementation15 Jun 2022 Saikat Chakraborty, Toufique Ahmed, Yangruibo Ding, Premkumar Devanbu, Baishakhi Ray

Pre-trained Generative Language models (e. g. PLBART, CodeT5, SPT-Code) for source code yielded strong results on several tasks in the past few years, including code generation and translation.

Code Translation Few-Shot Learning +1

VELVET: a noVel Ensemble Learning approach to automatically locate VulnErable sTatements

1 code implementation20 Dec 2021 Yangruibo Ding, Sahil Suneja, Yunhui Zheng, Jim Laredo, Alessandro Morari, Gail Kaiser, Baishakhi Ray

Automatically locating vulnerable statements in source code is crucial to assure software security and alleviate developers' debugging efforts.

Ensemble Learning

Towards Learning (Dis)-Similarity of Source Code from Program Contrasts

no code implementations ACL 2022 Yangruibo Ding, Luca Buratti, Saurabh Pujar, Alessandro Morari, Baishakhi Ray, Saikat Chakraborty

We pre-train our model with a much smaller dataset, the size of which is only 5% of the state-of-the-art models' training datasets, to illustrate the effectiveness of our data augmentation and the pre-training approach.

Clone Detection Contrastive Learning +2

Deep Learning based Vulnerability Detection: Are We There Yet?

1 code implementation3 Sep 2020 Saikat Chakraborty, Rahul Krishna, Yangruibo Ding, Baishakhi Ray

In this paper, we ask, "how well do the state-of-the-art DL-based techniques perform in a real-world vulnerability prediction scenario?".

Software Engineering

Patching as Translation: the Data and the Metaphor

1 code implementation24 Aug 2020 Yangruibo Ding, Baishakhi Ray, Premkumar Devanbu, Vincent J. Hellendoorn

Given these findings, we demonstrate how a more principled approach to model design, based on our empirical findings and general knowledge of software development, can lead to better solutions.

General Knowledge Program Repair +1

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