Tianyu Zhao¹, Xiaoli Zhao², Kenny S. L. Cheah^3,*, Ye Zhang³

International Journal of Mental Health Promotion, Vol.27, No.12, pp. 2023-2038, 2025, DOI:10.32604/ijmhp.2025.071322 - 31 December 2025

Abstract Background: Despite access to university counseling services, many students underutilize them due to cultural stigma, language barriers, and perceived irrelevance. As a result, ChatGPT has emerged as an informal, always-available support system. This study investigates how international PhD students in Malaysia navigate loneliness, mental well-being, and social disconnection through interactions with Generative AI (mainly ChatGPT. Methods: Using a mixed-methods design, the study surveyed 155 international doctoral students and analyzed quantitative responses across four dimensions: loneliness, well-being (WHO-5), perceived social support, and AI-facilitated emotional support. Additionally, open-ended responses were examined using Latent Dirichlet Allocation (LDA) to identify… More >

Muhammad Asif Khan¹, Dildar Hussain², Bhuyan Kaibalya Prasad³, Irfan Ullah⁴, Inayat Khan⁵, Jawad Khan^6,*, Yeong Hyeon Gu^2,*, Pavlos Kefalas⁷

CMC-Computers, Materials & Continua, Vol.85, No.3, pp. 5451-5468, 2025, DOI:10.32604/cmc.2025.069134 - 23 October 2025

Abstract Dialogue State Tracking (DST) is a critical component of task-oriented spoken dialogue systems (SDS), tasked with maintaining an accurate representation of the conversational state by predicting slots and their corresponding values. Recent advances leverage Large Language Models (LLMs) with prompt-based tuning to improve tracking accuracy and efficiency. However, these approaches often incur substantial computational and memory overheads and typically address slot extraction implicitly within prompts, without explicitly modeling the complex dependencies between slots and values. In this work, we propose PUGG, a novel DST framework that constructs schema-driven prompts to fine-tune GPT-2 and utilizes its tokenizer… More >

Eleena Sarah Mathew^*

Journal on Artificial Intelligence, Vol.7, pp. 347-363, 2025, DOI:10.32604/jai.2025.069841 - 06 October 2025

Abstract This review paper explores advanced methods to prompt Large Language Models (LLMs) into generating objectionable or unintended behaviors through adversarial prompt injection attacks. We examine a series of novel projects like HOUYI, Robustly Aligned LLM (RA-LLM), StruQ, and Virtual Prompt Injection that compel LLMs to produce affirmative responses to harmful queries. Several new benchmarks, such as PromptBench, AdvBench, AttackEval, INJECAGENT, and RobustnessSuite, have been created to evaluate the performance and resilience of LLMs against these adversarial attacks. Results show significant success rates in misleading models like Vicuna-7B, LLaMA-2-7B-Chat, GPT-3.5, and GPT-4. The review highlights limitations… More >

Abu Saleh Musa Miah¹, Md Mahbubur Rahman Tusher², Md. Moazzem Hossain², Md Mamun Hossain², Md Abdur Rahim³, Md Ekramul Hamid⁴, Md. Saiful Islam⁴, Jungpil Shin^1,*

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.3, pp. 2573-2614, 2025, DOI:10.32604/cmes.2025.064168 - 30 June 2025

Abstract Advanced artificial intelligence technologies such as ChatGPT and other large language models (LLMs) have significantly impacted fields such as education and research in recent years. ChatGPT benefits students and educators by providing personalized feedback, facilitating interactive learning, and introducing innovative teaching methods. While many researchers have studied ChatGPT across various subject domains, few analyses have focused on the engineering domain, particularly in addressing the risks of academic dishonesty and potential declines in critical thinking skills. To address this gap, this study explores both the opportunities and limitations of ChatGPT in engineering contexts through a two-part… More >

David He^1,*, Miao He², Jay Yoon³

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.2, pp. 1955-1969, 2025, DOI:10.32604/cmes.2025.063975 - 30 May 2025

Abstract Full ceramic bearings are mission-critical components in oil-free environments, such as food processing, semiconductor manufacturing, and medical applications. Developing effective fault diagnosis methods for these bearings is essential to ensuring operational reliability and preventing costly failures. Traditional supervised deep learning approaches have demonstrated promise in fault detection, but their dependence on large labeled datasets poses significant challenges in industrial settings where fault-labeled data is scarce. This paper introduces a few-shot learning approach for full ceramic bearing fault diagnosis by leveraging the pre-trained GPT-2 model. Large language models (LLMs) like GPT-2, pre-trained on diverse textual data,… More >

Ilyas Haouam^*

Journal on Artificial Intelligence, Vol.7, pp. 85-114, 2025, DOI:10.32604/jai.2025.064145 - 27 May 2025

Abstract This study investigates the integration of Artificial Intelligence (AI) technologies—particularly natural language processing and machine learning—into qualitative research (QR) workflows. Our research demonstrates that AI can streamline data collection, coding, theme identification, and visualization, significantly improving both speed and accuracy compared to traditional manual methods. Notably, our experimental and numerical results provide a comprehensive analysis of AI’s effect on efficiency, accuracy, and usability across various QR tasks. By presenting and discussing studies on some AI & generative AI models, we contribute to the ongoing scholarly discussion on the role of AI in QR exploring its… More >

Stefan Ćirković¹, Vladimir Mladenović¹, Siniša Tomić², Dalibor Drljača², Olga Ristić^1,*

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 4409-4430, 2025, DOI:10.32604/cmc.2025.059696 - 06 March 2025

Abstract With the increasing use of web applications, challenges in the field of cybersecurity are becoming more complex. This paper explores the application of fine-tuned large language models (LLMs) for the automatic generation of synthetic attacks, including XSS (Cross-Site Scripting), SQL Injections, and Command Injections. A web application has been developed that allows penetration testers to quickly generate high-quality payloads without the need for in-depth knowledge of artificial intelligence. The fine-tuned language model demonstrates the capability to produce synthetic payloads that closely resemble real-world attacks. This approach not only improves the model’s precision and dependability but… More >

Verónica C. Tapia^1,2,*, Carlos M. Gaona²

Computer Systems Science and Engineering, Vol.49, pp. 1-17, 2025, DOI:10.32604/csse.2024.056979 - 03 January 2025

Abstract In recent years, automation has become a key focus in software development as organizations seek to improve efficiency and reduce time-to-market. The integration of artificial intelligence (AI) tools, particularly those using natural language processing (NLP) like ChatGPT, has opened new possibilities for automating various stages of the development lifecycle. The primary objective of this study is to evaluate the effectiveness of ChatGPT in automating various phases of software development. An artificial intelligence (AI) tool was developed using the OpenAI—Application Programming Interface (API), incorporating two key functionalities: 1) generating user stories based on case or process… More >

Nader A. Shayegh¹, Danae Byer¹, Yasmine Griffiths¹, Pamela W. Coleman², Leslie A. Deane², Jeremy Tonkin²

Canadian Journal of Urology, Vol.31, No.3, pp. 11880-11885, 2024

Abstract This article has no abstract. More >

Yash B. Shah, Anushka Ghosh, Aaron Hochberg, James R. Mark, Costas D. Lallas, Mihir S. Shah

Canadian Journal of Urology, Vol.31, No.5, pp. 12013-12018, 2024

Abstract Introduction: Patients seek support from online resources when facing a troubling urologic cancer diagnosis. Physician-written resources exceed the recommended 6-8th grade reading level, creating confusion and driving patients towards unregulated online materials like AI chatbots. We aim to compare the readability and quality of patient education on ChatGPT against Epic and Urology Care Foundation (UCF).
Materials and methods: We analyzed prostate, bladder, and kidney cancer content from ChatGPT, Epic, and UCF. We further studied readability-adjusted responses using specific AI prompting (ChatGPT-a) and Epic material designated as Easy to Read. Blinded reviewers completed descriptive textual analysis, readability analysis… More >