Using Peer Assessment Leveraging Large Language Models in Software Engineering Education

Learning Software Engineering principles, processes, methods and tools is a prerequisite to becoming a Software Engineer. The technological advancements and revolution in this new century are probing the boundaries of education and training in software engineering. This work tries to locate the shortcomings in existing approaches to Education in Software Engineering (ESE) in respect to today's technological advancements. We hereby proposed a new model for Education in Software Engineering to bridge the industry-academia gap.

Distribution network design is one of the most essential strategic decisions in logistics systems and supply chains, as it structures the network by determining the number of echelons and specifying the types, quantities, and locations of various facilities. This chapter presents decision-support models for distribution and logistics network design, covering both continuous location models (gravity location models) and discrete network design models (capacitated/uncapacitated and their relevant variants). Comprehensive numerical experiments based on the same case study offer a direct comparison of these different network design approaches. Furthermore, as one of the most disruptive technologies in Industry 5.0, the impact of generative AI (GenAI) and large language models (LLMs) on the research and education of distribution network design is thoroughly analyzed. Our experiments demonstrate that GenAI and LLMs are powerful tools in providing structured introductions to existing problems, guiding model selection and explanation, assisting with coding and code clarification, facilitating model comparison, and generating initial ideas for new research questions in distribution and logistics network design. However, they also face reliability and accuracy challenges, exhibit limited critical thinking capabilities, and struggle to address emerging research questions. Our findings offer valuable guidance for incorporating GenAI tools and LLMs into research and educational processes in distribution and logistics network design.

Generative AI in cybersecurity: A comprehensive review of LLM applications and vulnerabilities

AI models, particularly generative AI and large language models, reshape digital information ecosystems by curating and amplifying content through user engagement metrics. Despite their capacity to reduce bias and promote inclusivity, these models simultaneously amplify cognitive biases, entrench filter bubbles, and spread misinformation. The intensification of human–machine interaction and hyper-industrialization complicates this further, as large language models increasingly mediate how information is produced and consumed. Socio-technical agency describes how AI systems co-construct human behavior and societal norms through their design, yet their effects remain understudied in regions with limited technological infrastructure. This paper investigates AI’s influence on information dissemination, cognitive biases, and user agency across digital media environments in key regions of the Global South. Drawing on qualitative interviews and a survey of 580 media technology users in South Africa, Indonesia, India, the Philippines, and Brazil it examines how generative AI affects emotional engagement, exposure to content, and perceptions of digital truth. Framed by media ecology theory, the study evaluates AI as a cognitive extension that can both reinforce and challenge digital biases. The study proposes strategies for using generative AI to support information integrity while addressing the risks of polarization and exclusion. By centering perspectives from regions in the Global South, it contributes to more equitable discourse on AI governance, advocating regulatory and design solutions responsive to diverse media ecologies.

Agentic AI and Large Language Models (LLMs) are transforming how language is understood and generated while reshaping decision-making, automation, and research practices. LLMs provide underlying reasoning capabilities, and Agentic AI systems use them to perform tasks through interactions with external tools, services, and Application Programming Interfaces (APIs). Based on a structured scoping review and thematic analysis, this study identifies that core challenges of LLMs, relating to security, privacy and trust, misinformation, misuse and bias, energy consumption, transparency and explainability, and value alignment, can propagate into Agentic AI. Beyond these inherited concerns, Agentic AI introduces new challenges, including context management, security, privacy and trust, goal misalignment, opaque decision-making, limited human oversight, multi-agent coordination, ethical and legal accountability, and long-term safety. We analyse the applications of Agentic AI powered by LLMs across six domains: education, healthcare, cybersecurity, autonomous vehicles, e-commerce, and customer service, to reveal their real-world impact. Furthermore, we demonstrate some LLM limitations using DeepSeek-R1 and GPT-4o. To the best of our knowledge, this is the first comprehensive study to integrate the challenges and applications of LLMs and Agentic AI within a single forward-looking research landscape that promotes interdisciplinary research and responsible advancement of this emerging field.

Background/Objectives: Trichoscopy is an important diagnostic tool for hair and scalp disorders, but it requires significant expertise. Publicly available large language models (LLMs) are becoming more popular among both physicians and patients, yet their usefulness in trichology is unknown. We aimed to evaluate the diagnostic accuracy of four publicly available LLMs when interpreting trichoscopic images, as well as to compare their performance with that of dermatology residents, board-certified dermatologists, and trichology experts. Method: In this prospective comparative study, a preprocessed set of trichoscopic images was assessed in an online image-based survey. To reduced recognition bias from public image repositories, all images were structurally transformed while preserving diagnostic features. Fifteen dermatologists (five residents, four board-certified dermatologists, six trichology experts) provided a suspected diagnosis (SD), and up to three the differential diagnoses (DD). Four LLMs (ChatGPT-4o, Claude Sonnet 4, Gemini 2.5 Flash, and Grok-3) evaluated the images under the same conditions. Results: The overall diagnostic accuracy among 15 dermatologists was 58.1% (95% CI, 53.0–63.0) for SD and 68.3% (95% CI, 63.4–72.8) for SD + DD. Experts significantly outperformed residents and board-certified dermatologists. AI models achieved an accuracy of 18.2% (95% CI, 11.8–26.9) for SD and 44.4% (95% CI, 35.0–54.3) for SD + DD. Gemini 2.5 Flash performed best, with an accuracy of 62.5% for SD + DD. Agreement among dermatologists increased with experience (AC1 up to 0.65 for experts), while agreement among AI models was moderate to good (AC1 up to 0.70). Agreement between AI models and dermatologists was only slight to fair (AC1 = 0.06 for SD and 0.21 for SD + DD). All human-AI differences were statistically significant (p < 0.001). Conclusions: In trichology, publicly available LLMs currently underperform compared to human experts, especially in providing a single correct diagnosis. These models require further development and specialized training before they can reliably assist with trichological diagnoses in routine care.

The integration of generative AI (GenAI) and large language models (LLMs) in healthcare presents both unprecedented opportunities and challenges, necessitating innovative regulatory approaches. In this perspective, we discuss the risks of GenAI and LLM-based medical devices, the limitations of current medical device regulation frameworks when applied to GenAI or LLMs, and advocate for global collaboration in regulatory science research through engaging multidisciplinary expertise and focusing on the needs of diverse populations.

SummarySustained engagement in HIV care and adherence to antiretroviral therapy (ART) are essential for achieving the UNAIDS “95-95-95” targets. Despite increased ART access, disengagement from care remains a significant issue, particularly in sub-Saharan Africa. Traditional machine learning (ML) models have shown moderate success in predicting care disengagement, which would enable early intervention. We develop an enhanced large language model (LLM) fine-tuned with electronic medical records (EMRs) to predict people at risk of disengaging from HIV care in Tanzania and to provide interpretative insights into modifiable risk factors.MethodsWe developed a novel AI model by enhancing a pre-trained LLM (LLaMA 3.1, an open-source pre-trained LLM released by Meta) using routinely collected EMRs from Tanzania’s National HIV Care and Treatment Program from January 1, 2018, to June 30, 2023 (4,809,765 records for 261,192 people) to identify people at risk of disengaging from HIV care or developing adverse outcomes. Outcomes included risk of ART non-adherence, non-suppressed viral load, and loss to follow-up. Models were evaluated internally (Kagera region) and externally (Geita region), with performance compared against state-of-art ML models and zero-shot LLMs. Additionally, a team of HIV physicians in Tanzania assessed the LLM’s predictions along with LLM provided justifications for a subset of patient records to evaluate their clinical relevance and reasoning.FindingsThe enhanced LLMs consistently outperformed the supervised ML model and zero-shot LLMs across all outcomes in both internal and external validation datasets. When focusing on the 25% of PLHIV predicted as most likely to lost-to-follow-up (LTFU), the model correctly identified 78% (2,515 of 3,224) of people living with HIV (PLHIV) genuinely at risk in internal validation and 73% (7,105 of 9,733) in external validation. Attention score analysis indicated that the enhanced LLM focused on keywords such as gaps in follow-up care and ART adherence. The human expert evaluation showed alignment between clinician assessments and the LLM’s predictions in 65% of cases, with experts finding the model’s justifications reasonable and clinically relevant in 92.3% of aligned cases.InterpretationIf implemented in HIV clinics, this LLM-based AI model could help allocate resources efficiently and deliver targeted interventions, improving retention in care and advancing the UNAIDS “95-95-95” targets. By functioning like a clinician–analyzing patient summaries, predicting risks, and offering reasoning–the enhanced LLM could be integrated into clinical workflows to complement human expertise, facilitating timely interventions and informed decision-making. If implemented widely, this human-AI collaboration has the potential to improve health outcomes for people living with HIV and reduce onward transmission.FundingThe study was supported by a grant from the US National Institutes of Health (NIH): NIH NIMH 1R01MH125746.

IntroductionJournal clubs are integral to continuing medical education, promoting critical thinking and evidence-based learning. However, inconsistent engagement, reliance on faculty expertise, and the complexity of research articles can limit their effectiveness. Generative Artificial Intelligence (Gen AI), particularly Large Language Models (LLMs) offers a potential solution, but general-purpose LLMs may generate inaccurate responses (“hallucinations”). Retrieval-Augmented Generation (RAG) mitigates this by integrating AI-generated content with curated knowledge sources, ensuring more accurate and contextually relevant responses. This study explores the development and preliminary evaluation of a RAG-enhanced LLM to support journal club discussions.Materials and methodsA specialized LLM was deployed using Microsoft Azure’s GPT-4o. A vector database was created by embedding journal club articles using text-embedding-ada-002 (Version 2) for efficient information retrieval. A dedicated website provided user-friendly access. The study followed a design-based research (DBR) approach, engaging residents and faculty who interacted with the LLM before and during journal club sessions. Data collection included focus group discussions (FGDs) and questionnaires assessing engagement, usability, and impact.ResultsThe study involved a total of 13 residents and three faculty members as participants. 50% of residents reported a positive experience, while the rest had a neutral response, citing both advantages and limitations. The LLM improved article summarization, query responses, and engagement as reported by residents. Moreover, the faculty observed enhanced discussion quality and preparation whereas overall challenges included the need for precise prompts and occasional misleading responses.ConclusionThe study highlights the potential of a RAG-enhanced LLM to improve journal club engagement and learning. Future advancements in AI and open-source models may enhance accessibility, warranting further research.

Most of the principles and concepts that need to be taught in Software Engineering courses are hard to share the realistic experiences because it is difficult to give the student practical exposure to the insight and processes involved. This paper presents an innovative framework tailored for the establishment of an immersive learning environment within the context of a Software Engineering Project course. The overarching objective is to effectively tackle the inherent challenges associated with teaching intricate software engineering concepts, notably Agile Scrum and Team Software Process (TSPi). Conventional pedagogical approaches often prove inadequate in providing a comprehensive and engaging learning experience for students, educators and stakeholders. In response, our study introduces a pioneering immersive learning approach, offering a robust solution to this educational gap. To gauge the framework's efficacy and pertinence, we conducted online surveys, specifically targeting third-year students enrolled in the Software Engineering Laboratory course and the project stakeholders involved. These surveys were instrumental in collecting valuable feedback on the practicality and impact of our approach in enhancing the teaching and learning processes. This study presents a thorough exposition encompassing the framework's conceptualization, implementation and iterative evolution. Our research outcomes reveal that our immersive learning approach has successfully met the predefined course objectives, effectively addressing the intrinsic challenge of imparting hands-on experiences associated with software engineering principles and concepts. As a significant contribution to the ongoing initiatives aimed at elevating software engineering education, our study underscores the importance of providing students with tangible exposure to vital concepts such as Agile Scrum and TSPi. Moreover, this paper delineates the collaborative journey involved in the creation, execution and refinement of the course framework. Ultimately, our research endeavours to evaluate the degree to which our innovative framework aligns with the objectives established by both students and stakeholders. By doing so, it underscores the transformative potential of our approach in reshaping the landscape of software engineering education, ultimately enhancing its effectiveness and relevance.

This article examines the transformative impact of generative AI and Large Language Models (LLMs) in the banking sector, analyzing both the opportunities and challenges of this technological evolution. The article traces AI's progression in financial services from early rule-based systems to today's sophisticated generative models, identifying key strategic applications across customer-facing services, operational efficiency, risk management, and regulatory compliance. The implementation barriers including data privacy concerns, algorithmic bias, explainability challenges, and varying cost-benefit considerations across institution sizes, the research proposes a structured integration framework tailored to different banking segments. This framework encompasses phased implementation strategies, governance protocols, human-AI collaboration models, specialized training methodologies, and partnership ecosystems. The article concludes by exploring emergent trends, research gaps, policy recommendations, strategic considerations for executives, and projections for long-term industry transformation, providing a balanced assessment of how generative AI is reshaping the banking landscape.

Large Language Models (LLM) like ChatGPT and Gemini have potential in nutrition applications, but recent studies suggest they provide inaccurate dietary advice. The aim of this study was to evaluate the most commonly used LLMs, ChatGPT and Gemini, for dietary recommendations for patients with irritable bowel syndrome (IBS). Various tools were used to assess the responses of LLMs in this study. The Guideline Compliance Score was created using IBS guidelines. The quality of the responses provided by LLMs was assessed using The Global Quality Score (GQS) and Completeness, Lack of Misinformation, Evidence, Appropriateness, Relevance (CLEAR) tool. Understandability and actionability were assessed using the Patient Education Materials Assessment Tool (PEMAT). The readability of ChatGPT and Gemini's responses was evaluated using Flesch Reading Ease (FRE) and Flesch Kincaid Grade Level (FKGL). This study found that most responses from ChatGPT (70%) and Gemini (57.5%) were compliant with the guidelines, but there was no significant difference in guideline compliance, quality, understandability, actionability, or readability scores (p > 0.05). The CLEAR tool showed a moderate positive correlation with PEMAT actionability (r = 0.467, p = 0.038) and understandability (r = 0.568, p = 0.009), a strong positive correlation with GQS (r = 0.611, p = 0.004). In addition, FRE and FKGL had a strong negative correlation (r = -0.784, p < 0.001), while the Guideline Compliance Score showed a moderate negative correlation with FRE (r = -0.537, p = 0.015). The study emphasizes the need for further model improvements before relying solely on LLMs in clinical nutrition practice, emphasizing the importance of dietitians' recommendations and the collaboration between AI models and healthcare teams.

CAMERON VU, Dept of Computer Science and Math &amp; ENGR, Shepherd University, Shepherdstown, WV, 25443, and DARIA PANOVA, Dept of Computer Science and Math &amp; ENGR, Shepherd University, Shepherdstown, WV, 25443, and JOSIAH KOWALSKI, Dept of Computer Science and Math &amp; ENGR, Shepherd University, Shepherdstown, WV, 25443, and Dr. W. LIAO (Faculty Advisor), Dept of Computer Science and Math &amp; ENGR, Shepherd University, Shepherdstown, WV, 25443, and Dr. O. Guzide (Faculty Advisor), Dept of Computer Science and Math &amp; ENGR, Shepherd University, Shepherdstown, WV, 25443. Smart Parking Space Detection with Generative Artificial Intelligence and Large Language Models. The increasing relevance of generative AI and large language models is reshaping various sectors of modern society. These advancements have spurred notable progress in fields such as healthcare, finance, and education. Yet, the application of AI extends beyond expert domains, offering simplified solutions to everyday tasks for the general populace. This project harnesses the power of generative artificial intelligence and large language models to develop a practical application: smart parking space detection. By leveraging these technologies, individuals can effortlessly ascertain the availability of parking spots in monitored lots via camera or photographic monitoring, facilitated by a straightforward algorithm. The overarching objective is twofold: to engineer a user-friendly system utilizing generative AI principles and to demonstrate the potential for such technologies to enhance the daily experiences of ordinary individuals.

Critical thinking and creative thinking skills are needed to improve the quality and competitive human resources. Therefore, the application of appropriate learning models is expected to stimulate students' critical thinking and creative thinking skills. This research aims to improve critical thinking and creative thinking skill scores using the ASICC learning model. This type of research is classroom action research which is carried out in 2 cycles, with 3 meetings in each cycle. Data on students' critical thinking and creative thinking skills were collected using essay tests on science learning materials. Data analysis was carried out by comparing the N-gain scores in cycle 1 and cycle 2 for students' critical thinking and creative thinking skills. The results of the research revealed that there was an increase that occurred in cycle 2, namely 5.6% in the aspects of moderate critical thinking skills and high creative thinking, as well as in the aspects of critical thinking skills and high creative thinking by 5.6%. Meanwhile, in the previous cycle, these two aspects did not have a high category. Another result found from this research is that students who have low critical thinking skills do not necessarily have low creative thinking skills. This is because students who have low critical thinking skills may have moderate creative thinking skills or vice versa. Thus, the application of the ASICC learning model is effective in improving the scores of critical thinking skills and creative thinking skills of students at Junior High School 5 Kertosono.

Burnout has become a significant concern in high-stress industries, impacting mental health and productivity. Traditional burnout management solutions lack real-time adaptability and personalized intervention strategies. This research explores an AI-driven burnout management mechanism leveraging Generative AI, MongoDB Atlas, Python, and Large Language Models (LLMs) to provide real-time detection, personalized coping strategies, and predictive analytics. The system collects and stores user responses, behavioral patterns, and sentiment data in MongoDB Atlas, while LLMs analyze and generate tailored burnout mitigation recommendations. Experimental results demonstrate the effectiveness of the proposed approach in early burnout detection, personalized intervention, and user engagement, showing improvements in stress reduction and work-life balance. The proof of concept for AI-powered burnout detection and intervention demonstrates the technical feasibility of using Large Language Models (LLMs), Generative AI, MongoDB Atlas, and Python-based automation for real-time mental health support. The system successfully classifies burnout severity using LLMs trained on sentiment analysis, achieving an accuracy of 91.2%, which significantly outperforms traditional rule-based sentiment models. The use of MongoDB Atlas for scalable data storage ensures real-time burnout tracking, while FastAPI-based backend automation allows for seamless integration across platforms. Furthermore, Generative AI provides personalized stress interventions, dynamically adapting to user feedback and improving engagement. These technical validations highlight how AI-driven burnout management can be scalable, real-time, and enterprise-ready, paving the way for AI-powered diagnostics in mental health applications across various industries.