Balancing AI and authenticity: EFL students’ experiences with ChatGPT in academic writing DOI Creative Commons
Indah Werdiningsih,

Marzuki Marzuki,

Diyenti Rusdin

et al.

Cogent Arts and Humanities, Journal Year: 2024, Volume and Issue: 11(1)

Published: Aug. 19, 2024

This research explores the experiences of EFL students and their strategies when incorporating ChatGPT into academic writing process. A qualitative case study method was employed, involving three with different proficiency levels. Data were collected through semi-structured interviews. Key findings indicate that is valued for overcoming uncertainties, clarifying vocabulary, offering content suggestions, enhancing essay quality by allowing to focus on creative aspects. However, balancing AI tools human judgment crucial authenticity. raises concerns about authenticity work, highlighting need ethical guidelines fostering critical thinking. Its limitations, such as providing overly complex suggestions lacking cultural sensitivity, necessitate oversight. Students recognize importance using seeking feedback ensure work quality. Educators should develop use in writing, emphasizing thinking originality. Training programs teachers responsible integration are essential. Despite comprehensive approach, small sample size limits generalizability, reliance self-reported data introduces potential bias. Future involve larger, diverse samples incorporate objective measures mitigate

Language: Английский

Large Language Models for Software Engineering: A Systematic Literature Review DOI
Xinyi Hou, Yanjie Zhao, Yue Liu

et al.

ACM Transactions on Software Engineering and Methodology, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 20, 2024

Large Language Models (LLMs) have significantly impacted numerous domains, including Software Engineering (SE). Many recent publications explored LLMs applied to various SE tasks. Nevertheless, a comprehensive understanding of the application, effects, and possible limitations on is still in its early stages. To bridge this gap, we conducted systematic literature review (SLR) LLM4SE, with particular focus how can be exploited optimize processes outcomes. We selected analyzed 395 research papers from January 2017 2024 answer four key questions (RQs). In RQ1, categorize different that been employed tasks, characterizing their distinctive features uses. RQ2, analyze methods used data collection, preprocessing, highlighting role well-curated datasets for successful LLM implementation. RQ3 investigates strategies evaluate performance SE. Finally, RQ4 examines specific tasks where shown success date, illustrating practical contributions field. From answers these RQs, discuss current state-of-the-art trends, identifying gaps existing research, promising areas future study. Our artifacts are publicly available at https://github.com/xinyi-hou/LLM4SE_SLR .

Language: Английский

Citations

133
Materials science in the era of large language models: a perspective DOI Creative Commons
Ge Lei, R. Docherty, Samuel J. Cooper

et al.

Digital Discovery, Journal Year: 2024, Volume and Issue: 3(7), P. 1257 - 1272

Published: Jan. 1, 2024

This perspective paper explores the potential of Large Language Models (LLMs) in materials science, highlighting their abilities to handle ambiguous tasks, automate processes, and extract knowledge at scale across various disciplines.

Language: Английский

Citations

25
MCQGen: A Large Language Model-Driven MCQ Generator for Personalized Learning DOI Creative Commons
Ching Nam Hang, Chee Wei Tan, Pei-Duo Yu

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 102261 - 102273

Published: Jan. 1, 2024

In the dynamic landscape of contemporary education, evolution teaching strategies such as blended learning and flipped classrooms has highlighted need for efficient effective generation multiple-choice questions (MCQs). To address this, we introduce MCQGen, a novel generative artificial intelligence framework designed automated creation MCQs. MCQGen uniquely integrates large language model (LLM) with retrieval-augmented advanced prompt engineering techniques, drawing from an extensive external knowledge base. This integration significantly enhances ability LLM to produce educationally relevant that align both goals educators diverse needs students. The employs innovative engineering, combining chain-of-thought self-refine prompting enhance performance LLM. process leads are not only contextually challenging but also reflective common student misconceptions, contributing effectively personalized experiences enhancing engagement understanding. Our evaluations showcase effectiveness in producing high-quality MCQs various educational styles. demonstrates its potential reduce time expertise required MCQ creation, marking practical utility modern education. essence, offers robust solution MCQs, digital era.

Language: Английский

Citations

16
Exploring the Key Factors Influencing College Students’ Willingness to Use AI Coding Assistant Tools: An Expanded Technology Acceptance Model DOI Creative Commons

Zelin Pan,

Zhendong Xie,

Tingting Liu

et al.

Systems, Journal Year: 2024, Volume and Issue: 12(5), P. 176 - 176

Published: May 15, 2024

The application of artificial intelligence (AI) in programming assistance has garnered researchers’ attention for its potential to reduce learning costs users, increase work efficiency, and decrease repetitive coding tasks. However, given the novelty AI Coding Assistant Tools (AICATs), user acceptance is currently limited, factors influencing this phenomenon are unclear. This study proposes an expanded model based on Technology Acceptance Model (TAM) that incorporates characteristics AICAT users explore key affecting college students’ willingness use AICATs. Utilizing a survey methodology, 303 Chinese participants completed questionnaire. Factor analysis Structural Equation Modeling (SEM) results indicate users’ dependence worry (DW) about AICATs positively affects perceived risk (PR), which turn negatively impacts usefulness (PU) ease (PEOU), thus reducing use. Dependence concerns also impact trust (PT), while PT PU PEOU, thereby enhancing Additionally, user’s self-efficacy (SE) DW PEOU. discusses significance these findings offers suggestions developers foster promote widespread

Language: Английский

Citations

15
Towards an understanding of large language models in software engineering tasks DOI
Zibin Zheng, Kaiwen Ning,

Qingyuan Zhong

et al.

Empirical Software Engineering, Journal Year: 2024, Volume and Issue: 30(2)

Published: Dec. 26, 2024

Language: Английский

Citations

10
A comparative study of English and Japanese ChatGPT responses to anaesthesia-related medical questions DOI Creative Commons
Kazuo Ando,

Sato Masaki,

Shin Wakatsuki

et al.

BJA Open, Journal Year: 2024, Volume and Issue: 10, P. 100296 - 100296

Published: June 1, 2024

Language: Английский

Citations

9
An overview of recent advancements in hyperspectral imaging in the egg and hatchery industry DOI Creative Commons
Md Wadud Ahmed, Alin Khaliduzzaman, J.L. Emmert

et al.

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 230, P. 109847 - 109847

Published: Dec. 18, 2024

Language: Английский

Citations

8
A Systematic Literature Review on Using Natural Language Processing in Software Requirements Engineering DOI Open Access
Sabina-Cristiana Necula,

Florin Dumitriu,

Valerică Greavu-Şerban

et al.

Electronics, Journal Year: 2024, Volume and Issue: 13(11), P. 2055 - 2055

Published: May 24, 2024

This systematic literature review examines the integration of natural language processing (NLP) in software requirements engineering (SRE) from 1991 to 2023. Focusing on enhancement requirement processes through technological innovation, this study spans an extensive array scholarly articles, conference papers, and key journal reports, including data Scopus, IEEE Xplore, ACM Digital Library, Clarivate. Our methodology employs both quantitative bibliometric tools, like keyword trend analysis thematic mapping, qualitative content provide a robust synthesis current trends future directions. Reported findings underscore essential roles advanced computational techniques machine learning, deep large models refining automating SRE tasks. highlights progressive adoption these technologies response increasing complexity systems, emphasizing their significant potential enhance accuracy efficiency practices while also pointing challenges integrating artificial intelligence (AI) NLP into existing workflows. The exploration historical contributions emerging offers new insights dynamic interplay between advances practical applications SRE.

Language: Английский

Citations

6
Harnessing the Power of General-Purpose LLMs in Hardware Trojan Design DOI

Georgios Kokolakis,

Athanasios Moschos,

Angelos D. Keromytis

et al.

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 176 - 194

Published: Jan. 1, 2024

Language: Английский

Citations

6
The Use of AI in Software Engineering: Synthetic Knowledge Synthesis of Recent Research Literature DOI Open Access
Peter Kokol

Published: March 11, 2024

Artificial intelligence (AI) has witnessed an exponential increase in its use various applications. Recently, the academic community started to research and inject new AI-based approaches provide solutions traditional software engineering problems. However, a comprehensive holistic understanding of current status is missing. To close above gap, synthetic knowledge synthesis was used induce landscape contemporary literature on AI engineering. The resulted 15 categories five themes, namely natural language processing engineering, artificial management development life cycle, machine learning fault/defect prediction effort estimation, employment deep intelligent code management, mining repositories improve quality. most productive country China (n=2042), followed by United States (n=1193), India (n=934), Germany (n=445), Canada (n=381). A high percentage (n=47.4%) papers were funded, showing strong interest this topic. convergence can significantly reduce needed resources, quality, user experience, well-being developers.

Language: Английский

Citations

5