Traditional AI Research Articles

Optimizing LLM Strategies for Playing Mendikot using Prompt Engineering

This study investigates the integration of a large language model (LLM) enhanced by prompt engineering and game theory to effectively engage in the strategic card game Mendikot. By refining complex prompts and leveraging a tailored visual understanding of game dynamics, we significantly bolster the decision-making prowess of the LLM. Our methodology involved the systematic simplification of game prompts to facilitate deeper learning and faster response times, coupled with the implementation of a visual recognition system to interpret and react to game states dynamically. The results illustrate that the adapted LLM outperforms traditional AI approaches in strategic decision-making tasks, underscoring a substantial improvement in both the accuracy and efficiency of game-play. This research not only demonstrates a viable model for enhancing AI interaction in recreational gaming but also opens avenues for deploying advanced AI strategies in complex strategic environments, offering insights into the broader application of AI in leisure and competitive arenas. The findings suggest that AI can transcend conventional gaming roles, potentially transforming strategic gameplay in digital and physical platforms.

Artificial Intelligence based Leak Detection in Blended Hydrogen and Natural Gas Pipelines

In the transition towards a hydrogen-based energy system, the strategic use of pipelines is crucial for efficient hydrogen distribution. Leveraging existing natural gas pipelines to carry a mix of hydrogen and natural gas offers a cost-effective alternative to building new infrastructure. This study explores the development of a leak detection system compatible with existing pipelines, specifically tailored for the blended hydrogen and natural gas mix. Given the scarcity of leak data for blended hydrogen-natural gas pipelines, the study introduces a Real-Time Transient Model (RTTM) for blended gases, simulating leak dynamics to generate necessary data. Additionally, a leak detection system (LDS) is developed using a fusion of Convolutional Neural Network (CNN) and Explainable Artificial Intelligence (XAI) through Adaptive Neuro-Fuzzy Inference Systems (ANFIS). This LDS framework overcomes the “black box” issue common in AI-driven systems, enabling reliable detection. The integration of Explainable and traditional AI techniques holds promising implications for blended hydrogen pipelines by enhancing the safety and efficiency of hydrogen transportation, thereby mitigating economic and environmental impacts, and addressing public concerns.

Advancing Artificial Intelligence: The Potential of Brain-Inspired Architectures and Neuromorphic Computing for Adaptive, Efficient Systems

Brain-inspired AI architecture, also known as neuromorphic computing, seeks to emulate the structure and functionality of the human brain to create more efficient, adaptive, and intelligent systems. Unlike traditional AI models that rely on conventional computing frameworks, brain-inspired architectures leverage neural networks and synapse-like connections to perform computations more similarly to biological brains. This approach offers significant advantages, including lower power consumption, improved learning capabilities, and enhanced problem-solving efficiency, particularly in tasks that require complex pattern recognition and cognitive processes. This paper explores the key components of brain-inspired AI architectures, such as spiking neural networks (SNNs) and neuromorphic hardware, and reviews the latest advancements in this field. We examine their applications across diverse domains, including robotics, autonomous systems, and medical diagnostics, where brain-like adaptability and real-time learning are critical. Additionally, we analyze the challenges associated with scaling these architectures, including hardware constraints and the complexity of accurately mimicking human brain functionality. The potential for combining brain-inspired AI with current machine learning models is also discussed, highlighting future directions for achieving more advanced, efficient, and human-like artificial intelligence systems. This research contributes to the growing body of knowledge on neuromorphic computing and its promise in shaping the future of AI technologies.Moreover, brain-inspired AI architectures have the potential to surpass traditional AI systems in terms of real-time decision-making and learning efficiency, particularly in environments that require adaptive behavior. The use of spiking neural networks (SNNs) in these architectures allows for more biologically plausible models of neuron activity, which can lead to advancements in sensory processing and autonomous decision-making. As neuromorphic hardware continues to evolve, integrating it with existing AI frameworks could enhance both performance and scalability. However, replicating the brain's full complexity remains a significant challenge, particularly in terms of creating energy-efficient hardware capable of supporting large-scale neural networks. Despite these challenges, the development of brain-inspired AI promises to bridge the gap between artificial and human intelligence, offering transformative possibilities for various industries.

Investigating College Student Mental Health Needs and Barriers Using Natural Language Processing

College students’s mental health has been declining, despite efforts by universities to improve outreach and programming. Though a variety of resources are available, students, especially those who experience marginalization, often do not engage with them. LGBTQ+ students in Florida, in particular, may face unique challenges. To understand marginalized college students’s mental health experiences, we conducted ten focus group interviews (N = 65) with students with various marginalized identities. Using Natural Language Processing (NLP) techniques, we conducted sentiment analysis with respect to students’s responses on interview questions (e.g., mental health needs, how needs are met/not met) among LGBTQ+ and other minority groups. Overall, LGBTQ+ students yielded a more negative sentiment than the other groups, with a marginally significant (at 0.1 level) difference suggested by Wilcoxon rank sum test. This project presents a novel approach to leveraging traditional qualitative methods and AI, provides deeper understanding of the mental-health-related needs of marginalized college students, and practical implications for prevention and intervention efforts to promote college students’s mental health.

6937 A Rare Case of Pembrolizumab-induced Multiple Endocrinopathies Presenting with Acute Adrenal Crisis Secondary to Isolated ACTH Deficiency - A Case Report

Abstract Disclosure: R. Abdelmasih: None. W. Pan: None. Introduction: Pembrolizumab is an immune checkpoint inhibitor (ICI) that blocks programmed cell death receptor 1 (PD-1) which took a massive leap in the oncology world. However, we are still understanding more about its immune-related adverse events (irAEs). Here we report a case of adrenal crisis due to pembrolizumab-induced hypophysitis and adrenalitis. Case Description: A 74-year-old male with a history of left renal cell carcinoma post left nephrectomy 5 years ago, complicated with lung metastasis for which Pembrolizumab was started. 5 months after, patient developed hypothyroidism and was started on Levothyroxine. 3 months later, Patient presented with lethargy and hypotension. Physical exam revealed hypotension (MAP of 55), fever, and acute encephalopathy. AM cortisol 4.2 ug/dL, Patient was started on IV pressors and a stress dose of Hydrocortisone. Hemodynamics improved, and Hydrocortisone was tapered down. ACTH stimulation test revealed a subnormal response of cortisol 0.2, 1.7, and 2.7 ug/dL at 0, 30, and 60 minutes respectively in the setting of very low ACTH of < 1.5 pg/ml, other pituitary hormones were checked, revealing normal insulin-like growth factor was 116 ng/mL, LH 15.29 mIU/mL, and FSH 27.45 mIU/mL. TSH was high 15 mIU/mL and free T4 was 1.4 ng/dl, levothyroxine dose was increased, and hydrocortisone was maintained at 10 in am and 5 in pm with excellent response. Discussion:ICIs inhibit the immunological pathways that control T-cell activation, leading to multiple immune-related endocrinopathies. Thyroiditis is the most reported one (30%), though anti-PD1-induced hypophysitis is exceptionally rare (< 1%). To date, the pathophysiology of pembrolizumab-induced central AI is not clearly understood, it’s presumed that it causes lymphocytic hypophysitis often presenting with isolated ACTH deficiency. Also, Pembrolizumab-induced primary adrenal insufficiency has seldom been reported and not yet understood, interestingly, anti-steroidogenic enzyme antibodies were absent in those few most reported cases which suggests a different mechanism compared to traditional primary AI. We suggest that our patient had combined primary and secondary adrenal insufficiency based on ACTH stim test result with very low cortisol responses in the setting of very low ACTH, which we believe is what led to such severe presentation of adrenal crisis. Diagnosis of PD1-induced AI can be challenging due to the overlapping of advanced malignancy and AI presentation. A higher level of suspicion is prompted especially in patients who experienced other endocrine irAEs (as our patient who had PDL-1-induced hypothyroidism). We present this case to shed light on this rare yet potentially fatal endocrine adverse event that can be reversed by prompt diagnosis and timely management due to the increasing use of pembrolizumab. More cases are needed for a better understanding of such a rare adverse event. Presentation: 6/2/2024

A case study: Making decisions for sustainable university campus planning using GeoAI

The increasing availability of geospatial data, the development of AI and the availability of large computational capacities have contributed to the growing importance and potential of GeoAI. GeoAI has an important role in advancing traditional AI technologies and developing new ways to solve problems posed by the massive, complex, diverse and ever-increasing nature of geospatial data. Geospatial data is widely used in many scientific fields and applications such as smart cities, transportation, business, public health, public safety, resilience to natural disasters, climate change and many more. Especially because of the huge growth in population and the need to analyze United Nations sustainability impacts oblige the experts to utilize GeoAI. The future vision, smart cities and smart campuses provide acceleration in the IoT and planning with GeoAI. In this scope this preceding enlightens campus planning by GeoAI as beginning step of the digital twin mechanism. This article is applied to: (1) GeoAI and campus planning techniques; (2) QGIS and KooMap utilization for AI based image recognition; (3) interpreting the output of GeoAI based map and giving sustainability recommendations related with campus planning; (4) Strengths and shortcomings of the research. GeoAI usage is proven as a beneficial way to make decisions on university campus by using automatically recognized satellite images. It is the first step for digital campus management system.

AI-Driven Waste Management Solutions in the Mining Industry: Reducing Environmental Impact

Soil, water, and air pollution are mainly resulted from the waste of mining industry. This ecological pollution resulted from mining activities must be managed and reduced effectively. With the emergence of AI, AI has the ability to help in driving an innovative and technological waste management model. The capacity of AI in predicting, modelling and automating waste management process will be studied through the use of the theory and approach based on Machine learning’s methodologies and algorithms. A comparative analysis between traditional methods and AI integrated methods of waste management will be conducted to evaluate the effectiveness of AI in driving waste management. Thus, this will require a specific case of mining activity to be studied. The data collection and data analysis consist of conducting a literature review and documents analysis, which includes a qualitative and quantitative analysis. All in all, the study will assess the effectiveness, operationality, efficiency and economic viability of AI-driven methods, in reducing pollution from mining activities. The results will emphasize the significant enhancement brought by AI-driven waste management. The prediction made by AI in the waste production will be demonstrated as accurate and optimizing waste discharge methods. This improvement is crucial in the reduction of environmental impact of mining activities. Seen as efficient, sustainable and cos-effective operations, the AI-driven waste management will transform and improve the environmental protection in the mining industry. The research offers innovative recommendations to stakeholders such as mining companies, policymakers and researchers.

From Near-Sensor to In-Sensor: A State-of-the-Art Review of Embedded AI Vision Systems.

In modern cyber-physical systems, the integration of AI into vision pipelines is now a standard practice for applications ranging from autonomous vehicles to mobile devices. Traditional AI integration often relies on cloud-based processing, which faces challenges such as data access bottlenecks, increased latency, and high power consumption. This article reviews embedded AI vision systems, examining the diverse landscape of near-sensor and in-sensor processing architectures that incorporate convolutional neural networks. We begin with a comprehensive analysis of the critical characteristics and metrics that define the performance of AI-integrated vision systems. These include sensor resolution, frame rate, data bandwidth, computational throughput, latency, power efficiency, and overall system scalability. Understanding these metrics provides a foundation for evaluating how different embedded processing architectures impact the entire vision pipeline, from image capture to AI inference. Our analysis delves into near-sensor systems that leverage dedicated hardware accelerators and commercially available components to efficiently process data close to their source, minimizing data transfer overhead and latency. These systems offer a balance between flexibility and performance, allowing for real-time processing in constrained environments. In addition, we explore in-sensor processing solutions that integrate computational capabilities directly into the sensor. This approach addresses the rigorous demand constraints of embedded applications by significantly reducing data movement and power consumption while also enabling in-sensor feature extraction, pre-processing, and CNN inference. By comparing these approaches, we identify trade-offs related to flexibility, power consumption, and computational performance. Ultimately, this article provides insights into the evolving landscape of embedded AI vision systems and suggests new research directions for the development of next-generation machine vision systems.

The Impact of a Digital Game-Based AI Chatbot on Students’ Academic Performance, Higher-Order Thinking, and Behavioral Patterns in an Information Technology Curriculum

In the age of intelligence, information technology (IT) education has become the focus of attention in the education sector. However, traditional teaching methods fall short in motivating students and fostering higher-order thinking and have difficulty providing a personalized learning experience. Although AI chatbots can provide instant feedback as an innovative teaching tool, it is still challenging to fully enhance learner engagement. Based on this, this study developed a digital game-based AI chatbot system to enhance students’ learning experience through digital game-based learning strategies. This study utilized a quasi-experimental design with the experimental group using a digital game-based AI chatbot and the control group using a traditional AI chatbot. A comparison was made between the two groups concerning student learning performance in IT courses, higher-order thinking (including problem-solving, computational thinking, and creativity), learning motivation, and flow experience. In addition, the behavioral patterns of high-achieving and low-achieving students in the experimental group were analyzed. The results showed that the experimental group was significantly better than the control group in academic performance, problem-solving, computational thinking, learning motivation, and flow experience, but there was no significant difference in creativity tendency. Behavioral pattern analysis showed that high-achieving students in the experimental group showed more systematic learning strategies, while low-achieving students relied more on immediate feedback and external help, but both high- and low-achieving groups were able to actively talk to the AI chatbot and actively explore problem-solving strategies in the digital game. Therefore, AI chatbots based on digital games can be effectively used in IT courses to help students construct knowledge and develop higher-order thinking.

An extended de Bruijn graph for feature engineering over biological sequential data

In this study, we introduce a novel de Bruijn graph (dBG) based framework for feature engineering in biological sequential data such as proteins. This framework simplifies feature extraction by dynamically generating high-quality, interpretable features for traditional AI (TAI) algorithms. Our framework accounts for amino acid substitutions by efficiently adjusting the edge weights in the dBG using a secondary trie structure. We extract motifs from the dBG by traversing the heavy edges, and then incorporate alignment algorithms like BLAST and Smith–Waterman to generate features for TAI algorithms. Empirical validation on TIMP (tissue inhibitors of matrix metalloproteinase) data demonstrates significant accuracy improvements over a robust baseline, state-of-the-art PLM models, and those from the popular GLAM2 tool. Furthermore, our framework successfully identified Glycine and Arginine-rich motifs with high coverage, highlighting it is potential in general pattern discovery.

Competition concerns with foundation models: a new feast for big tech?

ABSTRACT The paper explores how Generative AI intersects with Competition Law, focusing on Foundation Models (FMs) and Large Language Models (LLMs). It examines industry dynamics and identifies key competition issues like entry barriers, tying, leveraging, and acquisitions. It highlights the supply chain's importance and looks at how FMs are integrated into search software, chatbots, and productivity tools, particularly noting entry barriers such as computing power and data collection. It suggests that FMs might require new approaches to market delineation, possibly creating a separate relevant market for data. The paper also discusses various cases pertaining to tying and leveraging and highlights the difficulty in proving tying due to the blurred lines between traditional search engines and AI chatbots. It illustrates how competition assessments for acquisitions may require changes due to data being a highly flexible commodity for the industry. The paper concludes by calling for increased scrutiny and regulation for the industry.

A contemporary survey of recent advances in federated learning: Taxonomies, applications, and challenges

The Internet of Things (IoT) has embedded itself in our daily lives, offering smart services and AI-driven applications. However, traditional AI methods face challenges due to centralized data management in vast IoT networks and privacy concerns. Federated Learning (FL) solves this by training AI directly on distributed IoT devices, avoiding extensive data sharing. This article provides interested researchers of FL with an in-depth and up-to-date exploration of the multifaceted of FL in a privacy-centric era. This study is structured with three principal objectives. Firstly, within the realm of taxonomies for FL, the study aims to identify and categorize the existing frameworks utilized in FL research. Furthermore, it seeks to provide a thorough overview of how FL is delineated and conceptualized in current literature. Secondly, the study endeavors to explore the applications of FL by scrutinizing and classifying various use cases across diverse domains and industries. This objective aims to illuminate the applications and industries benefitting from FL implementations. Thirdly, the study addresses the inherent challenges in FL by examining the associated limitations. The study strives to offer insights into the technical and practical obstacles encountered in FL scenarios, contributing to a comprehensive understanding of the challenges within this dynamic field. This survey serves as a roadmap towards establishing sustainable massive IoT networks. Additionally, it paves the way for interested researchers to pursue and advance the vision of FL's evolving role in IoT.

IFNN: Enhanced interpretability and optimization in FNN via Adam algorithm

This investigation seeks to reconcile the interpretability of artificial intelligence with the imperative of maintaining optimal performance, through the introduction of the IFNN model. This model represents a sophisticated iteration of the Fuzzy Neural Network (FNN) paradigm, engineered for enhanced interpretability. At the heart of this innovation lies the application of the Adam optimization algorithm, integrated into a tri-layered architectural construct. This approach is deliberately designed to elevate the models' accuracy across an array of datasets, thereby positioning the IFNN model as an example of an interpretable AI system that does not compromise on precision.A seminal aspect of this model is its capacity to transmute logical neurons within the intermediary layer into clear fuzzy rules. This transformative process propels the model beyond the confines of traditional AI frameworks, ushering in a new era of transparency in the AI decision-making arena. Such progress is achieved through a meticulous fuzzy rule-based examination, anchored by an exhaustive appraisal of interpretability metrics, including but not limited to sensitivity, completeness, and the analysis of fuzzy rule consequents. These logical neurons, the progenitors of the aforementioned fuzzy rules, endow the model with the ability to engage in deep, interpretable analyses of data.The IFNN model has been tested through statistical analysis, interpretability assessments, and empirical validation against real-world datasets about sepsis identification, showcasing its unparalleled ability to unlock and articulate the complex knowledge embedded within data. This model represents a significant evolution in AI methodologies, providing a clear window into the rationale underpinning its decisions, achieved through an advanced fuzzy rule-based methodology and a full spectrum of interpretability metrics.

BIPOOLNET: An advanced UNet architecture for enhanced lane detection in autonomous vehicles

In the rapidly evolving landscape of autonomous vehicle technology, the imperative to bolster safety within smart urban ecosystems has never been more critical. This endeavor requires the deployment of advanced detection systems capable of navigating the intricacies of pedestrian, near-vehicle, and lane detection challenges, with a particular focus on the nuanced requirements of curved lane navigation – a domain where traditional AI models exhibit notable deficiencies. This paper introduces BIPOOLNET, an innovative encoder-decoder neural architecture, ingeniously augmented with a feature pyramid to facilitate the precise delineation of curved lane geometries. BIPOOLNET integrates max pooling and average pooling to extract critical features and mitigate the complexity of the feature map, redefining the benchmarks for lane detection technology. Rigorous evaluation using the TuSimple dataset underscores BIPOOLNET’s exemplary performance, evidenced by an unprecedented accuracy rate of 98.45%, an F1-score of 98.17%, and notably minimal false positive (1.84%) and false negative (1.09%) rates. These findings not only affirm BIPOOLNET’s supremacy over extant models but also signal a paradigm shift in enhancing the safety and navigational precision of autonomous vehicles, offering a scalable, robust solution to the multifaceted challenges posed by real-world driving dynamics.

Reinventing assessments with ChatGPT and other online tools: Opportunities for GenAI-empowered assessment practices

The recent emergence of generative artificial intelligence (GenAI) tools, such as ChatGPT, has brought profound changes to higher education. While many studies have examined the potential use of ChatGPT in teaching and learning, few have explored the opportunities to develop assessments that facilitate the use of multiple technological innovations (i.e. traditional AI and GenAI tools). We conducted qualitative research to address this gap. The assessments of an elective English course in Hong Kong were re-designed to incorporate GenAI and other tools. Students were asked to employ and reflect on their use of these tools for their writing assessments. We analyzed the written reflections of 74 students and conducted focus group interviews with 28 students. The results suggest that the students possess an acumen for choosing the appropriate online tools for specific purposes. When they can choose freely, they develop skills that allow them to evaluate and select between traditional AI and GenAI tools when appropriate. Some students mentioned concerns with the different features of the free and premium versions. The results of this study call for (1) assessment practices that allow the flexibility to use different AI tools and (2) the equitable use of various AI tools.

Generative Artificial Intelligence and Advertising

Generative artificial intelligence, the new buzzword in technology, is the next step in the evolution of traditional artificial intelligence. Unlike traditional AI that excels in data analyzing and automating processes, generative AI (GenAI) is a pioneer in creating new and original content. GenAI is very close to human intelligence, capable of logical thinking, imitating human behavior and armed with decision making capabilities. Generative AI creates new texts, images, music, 3D designs and codes, thus strongly influencing the activities, strategies, and consumer interactions of various industries. Key industries most affected by GenAI are banking and finance, retail and consumer goods, medicine and pharmaceuticals, education, media and marketing. In marketing, generative AI is significant in the process of personalization, content creation, audience engagement and interactions, performing the STP strategy (segmentation, targeting, positioning), market research, etc. Although it has great advantages, GenAI also has significant limitations, such as unresolved ethical issues, the spread of outdated or imprecise data, lack of legal regulation and control, etc. This paper, with the aid of secondary research, is aimed at exploring the possibilities of GenAI and its impact on marketing, especially advertising.

A novel deep learning framework for accurate melanoma diagnosis integrating imaging and genomic data for improved patient outcomes.

Melanoma is one of the most malignant forms of skin cancer, with a high mortality rate in the advanced stages. Therefore, early and accurate detection of melanoma plays an important role in improving patients' prognosis. Biopsy is the traditional method for melanoma diagnosis, but this method lacks reliability. Therefore, it is important to apply new methods to diagnose melanoma effectively. This study presents a new approach to classify melanoma using deep neural networks (DNNs) with combined multiple modal imaging and genomic data, which could potentially provide more reliable diagnosis than current medical methods for melanoma. We built a dataset of dermoscopic images, histopathological slides and genomic profiles. We developed a custom framework composed of two widely established types of neural networks for analysing image data Convolutional Neural Networks (CNNs) and networks that can learn graph structure for analysing genomic data-Graph Neural Networks. We trained and evaluated the proposed framework on this dataset. The developed multi-modal DNN achieved higher accuracy than traditional medical approaches. The mean accuracy of the proposed model was 92.5% with an area under the receiver operating characteristic curve of 0.96, suggesting that the multi-modal DNN approach can detect critical morphologic and molecular features of melanoma beyond the limitations of traditional AI and traditional machine learning approaches. The combination of cutting-edge AI may allow access to a broader range of diagnostic data, which can allow dermatologists to make more accurate decisions and refine treatment strategies. However, the application of the framework will have to be validated at a larger scale and more clinical trials need to be conducted to establish whether this novel diagnostic approach will be more effective and feasible.

Investigating the Evolving Landscape of Deepfake Technology: Generative AI's Role in it's Generation and Detection

The world of artificial intelligence is constantly changing, with Generative AI and Large Language Models (LLMs) leading the way in bringing new technological advancements. This paper offers a detailed look at these groundbreaking technologies and how they are shaping the digital world today. We explore the technical aspects of Generative AI and LLMs, explain their unique features, and compare them to traditional AI models.One of the key focuses of our research is the growing issue of DeepFakes—artificial intelligence-generated media that presents a significant challenge in verifying content. We conduct a thorough examination of few deepfake detection techniques out of which we will be implementing and analyzing one of them. Our research implements a framework for Deep Fake Image Detection. The suggested solution utilizes a RESNET-50(Residual Network with 50 layers) and MTCNN (Multi-task Cascaded Convolutional Networks) models for detecting whether the images are real or fake. This study conducts the Hypothesis testing for the proposed solution taking in consideration that the current Deepfake detection algorithms are less effective in detecting highly realistic Deepfakes compared to less sophisticated manipulations. By investigating the convergence of deep learning, neural networks, and sophisticated algorithms, we set the stage for advancements in AI-based content verification.

Unlocking Decision-Making Potential with Causal AI-Driven What-If Simulations

Abstract: This article explores the potential of causal AI-driven what-if simulations in enhancing decision-making across various industries. Causal AI uses theories and causal reasoning to figure out and model the underlying cause-and-effect relationships that govern a system or domain. It can make strong predictions even when it only has limited data. The article discusses the advantages of causal AI over traditional AI approaches and its ability to handle sparse data, enable counterfactual reasoning, and address bias issues. It delves into the applications of what-if simulations powered by causal AI in manufacturing, oil and gas, supply chain management, and contract management, presenting scenarios and demonstrating how causal AI can offer valuable insights and optimize decision-making. The article also highlights the challenges and opportunities associated with causal AI, including the need for domain expertise, integration with existing systems, interpretability and explainability, competitive advantage, positive social impact, research and development, and ethical considerations. The impact of causal AIdriven what-if simulations on decision-making across industries is substantial, enabling organizations to make informed decisions, mitigate risks, and seize opportunities in an ever-changing business landscape.

A GPT-Aided literature review process for total quality management and business excellence (2020-2023)

ABSTRACTS In an era of rapid technological evolution and competitive pressures, Total Quality Management (TQM) requires up-to-date literature reviews to reflect its evolving nature. This study addresses this need through a comprehensive analysis of TQM&BE journal articles from 2020 to 2023 and by introducing the LitRev-GPT framework. The research data was collected from the Scopus database, specifically targeting articles published in the TQM&BE journal from 2020 to 2023. This LitRev-GPT framework employs the Generative Pretrained Transformer (GPT) for efficient categorization and summarization of academic papers, setting new standards for reproducibility and methodological soundness. We identified emergent themes such as ‘Corporate Social Responsibility’, intertwining TQM with ethical practices, and ‘Industry 4.0’, showcasing TQM's adaptability to technological advancements. Additionally, trend analysis highlighted a sustained interest in foundational TQM themes, with a growing emphasis on innovation management. The LitRev-GPT framework demonstrates significant methodological advancements, enhancing the efficiency and depth of literature reviews beyond traditional AI capabilities.