English
Related papers

Related papers: CodeNet: A Large-Scale AI for Code Dataset for Lea…

200 papers

Ensuring that code accurately reflects the algorithms and methods described in research papers is critical for maintaining credibility and fostering trust in AI research. This paper presents a novel system designed to verify code…

Software Engineering · Computer Science 2025-02-04 Rajat Keshri , Arun George Zachariah , Michael Boone

Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet code generation remains a major challenge. Current approaches for obtaining high-quality code data primarily focus on (i) collecting large-scale…

Computation and Language · Computer Science 2025-02-18 Yichuan Ma , Yunfan Shao , Peiji Li , Demin Song , Qipeng Guo , Linyang Li , Xipeng Qiu , Kai Chen

Large-scale datasets have played a crucial role in the advancement of computer vision. However, they often suffer from problems such as class imbalance, noisy labels, dataset bias, or high resource costs, which can inhibit model performance…

Computer Vision and Pattern Recognition · Computer Science 2023-10-09 Zhijing Wan , Zhixiang Wang , CheukTing Chung , Zheng Wang

The introductory programming sequence has been the focus of much research in computing education. The recent advent of several viable and freely-available AI-driven code generation tools present several immediate opportunities and…

Human-Computer Interaction · Computer Science 2022-12-05 Brett A. Becker , Paul Denny , James Finnie-Ansley , Andrew Luxton-Reilly , James Prather , Eddie Antonio Santos

We present a benchmark dataset for evaluating method-level code generation task. The benchmark contains a dataset of 175 samples for automated evaluation and a dataset of 161 samples for manual evaluation. We also present a new metric for…

Software Engineering · Computer Science 2022-07-22 Yiyang Hao , Ge Li , Yongqiang Liu , Xiaowei Miao , He Zong , Siyuan Jiang , Yang Liu , He Wei

Large Language Models (LLMs) are advanced Artificial Intelligence (AI) systems that have undergone extensive training using large datasets in order to understand and produce language that closely resembles that of humans. These models have…

Software Engineering · Computer Science 2023-08-10 Alessio Buscemi

The recent rise in the popularity of large language models has spurred the development of extensive code datasets needed to train them. This has left limited code available for collection and use in the downstream investigation of specific…

Computation and Language · Computer Science 2025-12-30 Jonathan Katzy , Razvan Mihai Popescu , Arie van Deursen , Maliheh Izadi

Source code clones pose risks ranging from intellectual property violations to unintended vulnerabilities. Effective and efficient scalable clone detection, especially for diverged clones, remains challenging. Large language models (LLMs)…

Software Engineering · Computer Science 2025-10-20 Muslim Chochlov , Gul Aftab Ahmed , James Vincent Patten , Yuanhua Han , Guoxian Lu , David Gregg , Jim Buckley

Logs have been widely adopted in software system development and maintenance because of the rich runtime information they record. In recent years, the increase of software size and complexity leads to the rapid growth of the volume of logs.…

Software Engineering · Computer Science 2023-09-14 Jieming Zhu , Shilin He , Pinjia He , Jinyang Liu , Michael R. Lyu

Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents…

Agentic AI coding tools such as Claude Code and OpenAI Codex execute multi-step coding tasks with limited human oversight. To steer these tools, developers create repository-level configuration artifacts (e.g., Markdown files) for…

Large language models (LLMs) have brought significant advancements to code generation and code repair, benefiting both novice and experienced developers. However, their training using unsanitized data from open-source repositories, like…

Software Engineering · Computer Science 2024-07-08 Jiexin Wang , Xitong Luo , Liuwen Cao , Hongkui He , Hailin Huang , Jiayuan Xie , Adam Jatowt , Yi Cai

AI modeling for source code understanding tasks has been making significant progress, and is being adopted in production development pipelines. However, reliability concerns, especially whether the models are actually learning task-related…

Software Engineering · Computer Science 2022-01-11 Sahil Suneja , Yufan Zhuang , Yunhui Zheng , Jim Laredo , Alessandro Morari

Qualitative data analysis provides insight into the underlying perceptions and experiences within unstructured data. However, the time-consuming nature of the coding process, especially for larger datasets, calls for innovative approaches,…

Human-Computer Interaction · Computer Science 2024-03-12 Elisabeth Kirsten , Annalina Buckmann , Abraham Mhaidli , Steffen Becker

Source Code Summarization is the task of writing short, natural language descriptions of source code. The main use for these descriptions is in software documentation e.g. the one-sentence Java method descriptions in JavaDocs. Code…

Computation and Language · Computer Science 2019-04-05 Alexander LeClair , Collin McMillan

Many software analysis methods have come to rely on machine learning approaches. Code segmentation - the process of decomposing source code into meaningful blocks - can augment these methods by featurizing code, reducing noise, and limiting…

Software Engineering · Computer Science 2019-07-23 Jacob Dormuth , Ben Gelman , Jessica Moore , David Slater

The size and complexity of software applications is increasing at an accelerating pace. Source code repositories (along with their dependencies) require vast amounts of labor to keep them tested, maintained, and up to date. As the…

Software Engineering · Computer Science 2024-06-14 Ivan R. Ivanov , Joachim Meyer , Aiden Grossman , William S. Moses , Johannes Doerfert

As text and code resources have expanded, large-scale pre-trained models have shown promising capabilities in code generation tasks, typically employing supervised fine-tuning with problem statement-program pairs. However, increasing model…

Computation and Language · Computer Science 2025-04-10 Nathanaël Beau , Benoît Crabbé

Despite long-standing efforts in accelerating scientific discovery with AI, building AI co-scientists remains challenging due to limited high-quality data for training and evaluation. To tackle this data scarcity issue, we present AutoSDT,…

Many software projects implement APIs and algorithms in multiple programming languages. Maintaining such projects is tiresome, as developers have to ensure that any change (e.g., a bug fix or a new feature) is being propagated, timely and…

Software Engineering · Computer Science 2023-09-13 Jiyang Zhang , Pengyu Nie , Junyi Jessy Li , Milos Gligoric