中文
相关论文

相关论文: An Empirical Study on the Effectiveness of Large L…

200 篇论文

Self-Admitted Technical Debt (SATD), cases where developers intentionally acknowledge suboptimal solutions in code through comments, poses a significant challenge to software maintainability. Left unresolved, SATD can degrade code quality…

软件工程 · 计算机科学 2025-01-20 Mohammad Sadegh Sheikhaei , Yuan Tian , Shaowei Wang , Bowen Xu

Self-admitted technical debt (SATD), referring to comments flagged by developers that explicitly acknowledge suboptimal code or incomplete functionality, has received extensive attention in machine learning (ML) and traditional (Non-ML)…

软件工程 · 计算机科学 2026-01-21 Niruthiha Selvanayagam , Taher A. Ghaleb , Manel Abdellatif

Self-Admitted Technical Debt (SATD) refers to circumstances where developers use textual artifacts to explain why the existing implementation is not optimal. Past research in detecting SATD has focused on either identifying SATD…

软件工程 · 计算机科学 2025-04-30 Edi Sutoyo , Paris Avgeriou , Andrea Capiluppi

Technical debt refers to suboptimal code that degrades software quality. When developers intentionally introduce such debt, it is called self-admitted technical debt (SATD). Since SATD hinders maintenance, identifying its categories is key…

软件工程 · 计算机科学 2025-10-24 Sota Nakashima , Yuta Ishimoto , Masanari Kondo , Tao Xiao , Yasutaka Kamei

Large Language Models (LLMs) are increasingly embedded in software via APIs like OpenAI, offering powerful AI features without heavy infrastructure. Yet these integrations bring their own form of self-admitted technical debt (SATD). In this…

软件工程 · 计算机科学 2025-09-26 Ahmed Aljohani , Hyunsook Do

Self-admitted technical debt (SATD) refers to comments in which developers explicitly acknowledge code issues, workarounds, or suboptimal solutions. SATD is known to significantly increase software maintenance effort. While extensive…

软件工程 · 计算机科学 2025-12-22 Shahidul Islam , Md Nahidul Islam Opu , Shaowei Wang , Shaiful Chowdhury

The development of Machine Learning (ML)- and, more recently, of Deep Learning (DL)-intensive systems requires suitable choices, e.g., in terms of technology, algorithms, and hyper-parameters. Such choices depend on developers' experience,…

软件工程 · 计算机科学 2024-09-19 Federica Pepe , Fiorella Zampetti , Antonio Mastropaolo , Gabriele Bavota , Massimiliano Di Penta

Upon evolving their software, organizations and individual developers have to spend a substantial effort to pay back technical debt, i.e., the fact that software is released in a shape not as good as it should be, e.g., in terms of…

软件工程 · 计算机科学 2023-08-21 Antonio Mastropaolo , Massimiliano Di Penta , Gabriele Bavota

Artificial Intelligence and Machine Learning have witnessed rapid, significant improvements in Natural Language Processing (NLP) tasks. Utilizing Deep Learning, researchers have taken advantage of repository comments in Software Engineering…

软件工程 · 计算机科学 2023-03-20 William Aiken , Paul K. Mvula , Paula Branco , Guy-Vincent Jourdan , Mehrdad Sabetzadeh , Herna Viktor

The emergence of open-source ML libraries such as TensorFlow and Google Auto ML has enabled developers to harness state-of-the-art ML algorithms with minimal overhead. However, during this accelerated ML development process, said developers…

软件工程 · 计算机科学 2025-12-01 Aaditya Bhatia , Foutse Khomh , Bram Adams , Ahmed E Hassan

The adoption of Large Language Models (LLMs) for code generation in data science offers substantial potential for enhancing tasks such as data manipulation, statistical analysis, and visualization. However, the effectiveness of these models…

Prior work has combined chain-of-thought prompting in large language models (LLMs) with programmatic representations to perform effective and transparent reasoning. While such an approach works well for tasks that only require forward…

计算与语言 · 计算机科学 2023-10-13 Xi Ye , Qiaochu Chen , Isil Dillig , Greg Durrett

Recent advancements in generative AI have led to the widespread adoption of large language models (LLMs) in software engineering, addressing numerous long-standing challenges. However, a comprehensive study examining the capabilities of…

The rapid adoption of Deep Learning (DL)-enabled systems has revolutionized software development, driving innovation across various domains. However, these systems also introduce unique challenges, particularly in maintaining software…

软件工程 · 计算机科学 2025-10-07 Gilberto Recupito , Vincenzo De Martino , Dario Di Nucci , Fabio Palomba

Language models (LMs) with less than 100B parameters are known to perform poorly on chain-of-thought (CoT) reasoning in contrast to large LMs when solving unseen tasks. In this work, we aim to equip smaller LMs with the step-by-step…

计算与语言 · 计算机科学 2023-10-17 Seungone Kim , Se June Joo , Doyoung Kim , Joel Jang , Seonghyeon Ye , Jamin Shin , Minjoon Seo

Developers often opt for easier but non-optimal implementation to meet deadlines or create rapid prototypes, leading to additional effort known as technical debt to improve the code later. Oftentimes, developers explicitly document the…

软件工程 · 计算机科学 2026-02-10 Ibuki Nakamura , Yutaro Kashiwa , Bin Lin , Hajimu Iida

Technical debt (TD) refers to the long-term costs associated with suboptimal design or code decisions in software development, often made to meet short-term delivery goals. Self-Admitted Technical Debt (SATD) occurs when developers…

软件工程 · 计算机科学 2026-04-28 Edi Sutoyo , Andrea Capiluppi

Context: Previous studies demonstrate that Machine or Deep Learning (ML/DL) models can detect Technical Debt from source code comments called Self-Admitted Technical Debt (SATD). Despite the importance of ML/DL in software development,…

软件工程 · 计算机科学 2024-08-23 Emmanuel Iko-Ojo Simon , Chirath Hettiarachchi , Alex Potanin , Hanna Suominen , Fatemeh Fard

This work investigates the applicability of recent generative Large Language Models (LLMs), such as the GPT series and Flan-T5, to ontology alignment for identifying concept equivalence mappings across ontologies. To test the zero-shot…

人工智能 · 计算机科学 2023-09-15 Yuan He , Jiaoyan Chen , Hang Dong , Ian Horrocks

Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we explore instruction finetuning with a particular focus on (1)…

‹ 上一页 1 2 3 10 下一页 ›