Emergent Threat Discovery: Unsupervised Machine Learning for Phishing Campaign Analysis

In today’s rapidly evolving business landscape, Artificial Intelligence (AI), and specifically Large Language Models (LLMs), are redefining how organizations operate, make decisions, and engage with customers. AI-driven technologies have become indispensable, providing businesses with powerful tools to streamline operations, derive actionable insights from vast data, and foster more meaningful customer interactions. For business leaders, scholars, and practitioners alike, understanding the transformative potential of AI isn’t just advantageous—it’s essential to staying competitive in an increasingly data-driven world.This editorial delves into recent scholarly advancements in LLM applications within business contexts, analyzing studies that explore AI’s potential across various domains, from decision support to creative industries. By introducing a structured framework, this editorial highlights key insights and contributions from recent studies, assessing their value to academia and industry. The following comparative analysis sheds light on how these innovations shape our understanding of AI’s role in business while pointing to future research directions.Puyt and Madsen's (2024) study stands out as a foundational exploration of LLM accuracy, assessing ChatGPT-4's ability to recount the history of the SWOT analysis-a vital business strategy tool. Their findings reveal that, while ChatGPT-4 effectively conveys general concepts, it struggles with detailed historical information, often producing inaccuracies or "hallucinations." This gap underscores the need for LLMs to be trained with verified academic data, particularly for strategic business applications that demand precision. This study not only contributes to the literature by proposing methods to evaluate AI accuracy in historical contexts but also highlights the importance of rigorous information vetting in industry settings where reliability is crucial.In contrast, Raikov et al. (2024) explore a hybrid intelligence model that combines LLM capabilities with explainable AI (XAI) principles to enhance human-machine collaboration. Their approach emphasizes cognitive semantics, improving transparency and decision-making efficiency. The hybrid model's real-time adaptability addresses the needs of complex, regulated industries such as finance and healthcare, where trust in AI decisions is paramount. Academically, this study provides a valuable addition to XAI literature by demonstrating how LLMs can bridge the gap between AI autonomy and human oversight, making it a model for future human-AI interactions in complex business environments.Another significant study by Mariotti and colleagues (2024) examines the integration of LLMs with enterprise knowledge graphs to enhance data-driven decision-making. By enabling organizations to leverage knowledge graphs for more accurate and scalable data retrieval, this research provides a robust framework for businesses seeking efficient knowledge management systems. The academic contribution here lies in advancing the dialogue between LLMs and knowledge graphs, emphasizing ethical data handling and quality standards essential for industry applications. For enterprises, the study offers practical solutions to achieve streamlined data management, balancing automation with privacy and security. 2024) take a different approach, investigating LLMs' role in creative industries, specifically within fashion design. They introduce a hybrid intelligence model that supports creative processes, allowing AI to complement rather than replace human ingenuity. While LLMs in this field demonstrate potential in automating repetitive design tasks and enhancing customer personalization, the study reveals limitations in AI's ability to handle spatial and stylistic nuances. This study's academic contribution lies in promoting human-AI co-creation, inspiring further research into AI applications across diverse creative sectors, including media and marketing.Collectively, these studies not only illuminate LLMs' transformative potential in business but also highlight critical ethical and operational considerations. Ensuring accuracy, transparency, and data privacy are vital to responsibly integrating AI into business workflows. Future research should focus on enhancing LLM accuracy, refining hybrid intelligence models, and exploring creative AI applications, all while maintaining ethical standards. As LLMs evolve, interdisciplinary collaborations will be essential to harness their full potential, making AI an ethical, effective, and innovative force in the business world.

The rapid integration of Large Language Models (LLMs) into critical societal domains, including healthcare, finance, and law, has created an urgent need for transparency and accountability. However, the inherent "black box" nature of these complex models presents a significant obstacle to understanding their decision-making processes, which can lead to issues of trust, bias, and unforeseen errors. This article provides a comprehensive review of the current state of Explainable Artificial Intelligence (XAI) for LLMs. We conduct a systematic analysis of existing XAI techniques, categorizing them into a novel taxonomy based on their underlying mechanisms: attention-based methods, feature attribution methods, mechanistic interpretability, and natural language explanations. The findings reveal the key challenges in achieving meaningful explainability, including the trade-offs between model performance and transparency, the computational cost of explanation generation, and the lack of standardized evaluation metrics. This paper introduces a conceptual framework for implementing and evaluating explainability in LLMs, offering practical guidelines for researchers and practitioners. By synthesizing the latest research, including insights into the internal mechanisms of models like Anthropic's Claude series, this article aims to bridge the gap between the demand for transparency and the technical complexities of LLM explainability, paving the way for more trustworthy and reliable AI systems.

Machine learning methods are proposed to mitigate the spread of fake Brazilian news about politics so as not to harm society. Supervised algorithms are explored, requiring labeled news to train. However, labeling a high volume of news can be complex, onerous, time-consuming, error-prone, and costly. Hence, large language models (LLMs) have been used to detect fake news once LLMs are unsupervised methods that can play the role of classifiers. Most fake news detection studies explore the OpenAI LLMs (require payment) and lack an empirical evaluation with other LLMs. However, several open-source models obtain comparative and state-of-the-art (SOTA) results. We highlight that these models have yet to be explored in detecting fake Brazilian news about politics, which is crucial as it directly impacts society. In this sense, we propose a new dataset for detecting fake Brazilian news about politics and an empirical evaluation of open-source LLMs and OpenAI LLMs. In our results, the LLM from Google (Gemma) outperformed the other six LLMs, including GPT-4, proving to be the most promising model for detecting fake news about Brazilian politics.

As AI becomes more powerful, it also becomes more complex. Traditionally, eXplainable AI (XAI) is used to make these models more transparent and interpretable to decision-makers. However, research shows that decision-makers can lack the ability to properly interpret XAI techniques. Large language models (LLMs) offer a solution to this challenge by providing natural language text in combination with XAI techniques to provide more understandable explanations. However, previous work has only explored this approach for inherently interpretable models–an understanding of how LLMs can assist decision-makers when using deep learning models is lacking. To fill this gap, we investigate how different augmentation strategies of LLMs assist decision-makers in interacting with deep learning models. We evaluate the satisfaction and preferences of decision-makers through a user study. Overall, our results provide first insights into how LLMs support decision-makers in interacting with deep learning models and open future avenues to continue this endeavor.

The emergence of Large Language Models (LLMs) has revolutionized how users access information, shifting from traditional search engines to direct question-and-answer interactions with LLMs. However, the widespread adoption of LLMs has revealed a significant challenge known as hallucination, wherein LLMs generate coherent yet factually inaccurate responses. This hallucination phenomenon has led to users' distrust in information retrieval systems based on LLMs. To tackle this challenge, this paper proposes Dynamic Retrieval Augmentation based on hallucination Detection (DRAD) as a novel method to detect and mitigate hallucinations in LLMs. DRAD improves upon traditional retrieval augmentation by dynamically adapting the retrieval process based on real-time hallucination detection. It features two main components: Real-time Hallucination Detection (RHD) for identifying potential hallucinations without external models, and Self-correction based on External Knowledge (SEK) for correcting these errors using external knowledge. Experiment results show that DRAD demonstrates superior performance in both detecting and mitigating hallucinations in LLMs. All of our code and data are open-sourced at https://github.com/oneal2000/EntityHallucination.

Explainable Artificial Intelligence (XAI) constitutes a foundational pillar of responsible AI deployment, addressing the opacity of data-driven decision systems by making their internal logic transparent, auditable, and contestable. This chapter provides a systematic account of explainability and interpretability across the full spectrum of AI models — from classical supervised learning algorithms such as decision trees, support vector machines, and gradient-boosted ensembles to contemporary Large Language Models (LLMs) built on transformer architectures. Beginning with a structured taxonomy of XAI properties — scope, stage, model-dependency, and output type — the chapter critically examines canonical explanation methods including SHAP, LIME, attention visualization, mechanistic circuit analysis, and counterfactual generation.

Cross site scripting (XSS) attacks are still one of the key threats to the security of web applications. With the increasingly evolving attack methods, traditional detection methods have a high false positive rate of detection results. This article proposes a new model: a cascaded detection architecture that combines Long Short Term Memory (LSTM) networks with Large Language Models (LLM) for detecting XSS malicious code attacks. This method first uses Word2vec for code vectorization, turning the malicious code into vector data predictable by LSTM. Then, LSTM detects the vectorized malicious code and classifies the samples as malicious , benign , or suspicious. The malicious code samples classified as suspicious will be sent to LLM for detailed analysis again. The experimental results obtained show that compared to independent LSTM for malicious code detection, the cascaded method of LSTM and LLM has an accuracy rate of up to 97.8% and a 42% reduction in false positive rate, especially for some Base64 and URL encoded malicious code detection with higher accuracy. At the same time, to ensure detection speed, only 8.3% of the malicious code samples were extracted for detection.

The integration of large language models (LLMs) into medical diagnostics has garnered substantial attention due to their potential to enhance diagnostic accuracy, streamline clinical workflows, and address health care disparities. However, the rapid evolution of LLM research necessitates a comprehensive synthesis of their applications, challenges, and future directions. This scoping review aimed to provide an overview of the current state of research regarding the use of LLMs in medical diagnostics. The study sought to answer four primary subquestions, as follows: (1) Which LLMs are commonly used? (2) How are LLMs assessed in diagnosis? (3) What is the current performance of LLMs in diagnosing diseases? (4) Which medical domains are investigating the application of LLMs? This scoping review was conducted according to the Joanna Briggs Institute Manual for Evidence Synthesis and adheres to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews). Relevant literature was searched from the Web of Science, PubMed, Embase, IEEE Xplore, and ACM Digital Library databases from 2022 to 2025. Articles were screened and selected based on predefined inclusion and exclusion criteria. Bibliometric analysis was performed using VOSviewer to identify major research clusters and trends. Data extraction included details on LLM types, application domains, and performance metrics. The field is rapidly expanding, with a surge in publications after 2023. GPT-4 and its variants dominated research (70/95, 74% of studies), followed by GPT-3.5 (34/95, 36%). Key applications included disease classification (text or image-based), medical question answering, and diagnostic content generation. LLMs demonstrated high accuracy in specialties like radiology, psychiatry, and neurology but exhibited biases in race, gender, and cost predictions. Ethical concerns, including privacy risks and model hallucination, alongside regulatory fragmentation, were critical barriers to clinical adoption. LLMs hold transformative potential for medical diagnostics but require rigorous validation, bias mitigation, and multimodal integration to address real-world complexities. Future research should prioritize explainable artificial intelligence frameworks, specialty-specific optimization, and international regulatory harmonization to ensure equitable and safe clinical deployment.

Abstract: Interview performance can be considered an essential factor of employability, and most job seekers cannot access realistic, adaptive interview preparation aids. The current AI-based HR interview systems are mainly aimed at candidate screening to hire and lack the interactive practice systems with extensive development capabilities. The following paper introduces a sophisticated AI-based HR interview simulator that is specifically developed and focused on interview preparation and covers the main shortcomings of the existing systems such as a lack of transparency, insufficient quality of feedback, a lack of multimodal analysis, and poor adaptability. The suggested system has Large Language Models (LLMs) and reinforcement learning to generate questions dynamically and context-sensitive, and Automatic Speech Recognition (ASR), Natural Language Processing (NLP), and Computer Vision to perform multimodal assessment. The system records cognitive and affective aspects of the interview performance based on the attention-based multimodal fusion and gives a transparent and hierarchical feedback to provide fair and inclusive interview preparation. The study would add to the provision of a thorough framework on responsible AI-based interview preparation, the importance of explainability, fairness, and holistic skill development. Active keywords: AI interview simulation, explainable AI, multimodal assessment, reinforcement learning, bias mitigation, adaptive questioning, interview preparation, large language models, fairness auditing.

We fine‐tuned and compared several encoder‐based Transformer large language models (LLM) to predict differential item functioning (DIF) from the item text. We then applied explainable artificial intelligence (XAI) methods to identify specific words associated with the DIF prediction. The data included 42,180 items designed for English language arts and mathematics summative state assessments among students in grades 3 to 11. Prediction ranged from .04 to .32 among eight focal and reference group pairs. Our findings suggest that many words associated with DIF reflect minor subdomains included in the test blueprint by design, rather than construct‐irrelevant content that may need to be removed from assessments. This may explain why qualitative reviews of DIF items often yield inconclusive results. Our approach can be used to (1) screen words associated with DIF during the item‐writing process for immediate revision to reduce preventable adverse DIF, (2) assist traditional DIF item reviews by highlighting key words, or (3) use DIF prediction as an alternative when obtaining sufficient sample size for traditional DIF analyses is impossible. Extensions of this research can enhance the assessment fairness, especially programs that lack resources to build high‐quality items, and among smaller subpopulations with insufficient sample sizes for traditional DIF analyses. See source code here .

Explainable AI (XAI) techniques like SHAP provide valuable insights into machine learning model predictions by quantifying feature contributions. However, interpreting these quantitative outputs remains unintuitive for many clinicians, hindering their practical adoption in clinical decision-making. This exploratory feasibility study aims to propose and evaluate a prompting framework designed to guide large language models (LLMs) in generating consistent, clinically relevant explanations from SHAP values. We developed a structured zero-shot prompting framework incorporating variable definitions, safety principles, and a three-step reasoning process; (1) key risk factors, (2) prediction-outcome reconciliation, (3) clinical recommendations. This framework guided GPT-4 to explain SHAP-based predictions from an ICU extubation failure model (trained on MIMIC-III data). The framework’s performance was assessed using quantitative consistency metrics (entropy, accuracy) and a qualitative clinician survey (n = 7). The LLM achieved a fidelity of 0.783 and entropy of 0.226, indicating consistent structured reasoning. On a 5-point Likert scale, clinicians rated the LLM-generated explanations as helpful (mean: 3.94 ± 0.48) and safe (4.21 ± 0.68). However, critical care specialists assigned lower scores than non-critical care physicians (helpfulness: 3.48 vs. 4.29; safety: 3.45 vs. 4.79), suggesting domain-specific caution in perceived utility. A structured prompting framework shows feasibility in leveraging LLMs to enhance the clinical interpretability of SHAP explanations. This methodological approach warrants further investigation and refinement for broader clinical application.

Over the past five years, medical question answering (QA) has witnessed rapid advancements, driven by the evolution of large language models (LLMs), explainability techniques, and the growing emphasis on human-centered AI in healthcare. In clinical settings, where decisions directly impact patient outcomes, the need for transparency, interpretability, and trust in AI-generated answers is not merely beneficial but essential..Traditional QA systems, although reasonably accurate, often lack explainability, thus continuing to function as black boxes. This opacity raises fundamental concerns about accountability, safety in high-stakes medical domains. We introduce ExplainMed++, a novel system designed to generate human-centered medical QA summaries with intelligible explanations. Our approach enhances the interpretability and reliability of QA outputs by fine-tuning state-of-the-art LLMs using domain-specific datasets such as MedQA. This design is influenced by cognitive models of physician decision-making and recent progress in self-rationale LLMs. This literature increasingly highlights the limitations of accuracy-centric but also provides evidence-based and clinically aligned explanations.We incorporate an explanation module that leverages retrieval-augmented generation and reflective reasoning to align model outputs with clinical reasoning patterns. This literature review synthesizes findings from 70 influential studies published between 2020 and 2025,spanning foundational work in biomedical NLP, explainable AI(XAI), highlighting key technological advances, unresolved challenges, and promising future directions in explainable medical QA. These works collectively illuminate both the promise and limitations of current methodologies, including prompt-based reasoning and counterfactual generation. ExplainMed++ contributes to this landscape by bridging the gap between model performance and clinical usability and also, advancing both the performance and the trust-worthiness of QA systems in healthcare.

The massive digitalization of the communication environment has created fertile ground for increasingly sophisticated social engineering attacks, which exploit human psychology rather than technical flaws. Online criminal activity: Today, fraudsters hijack real-time conversations across voice calls, chat platforms, and emails to trick individuals and organizations into divulging private information or approving fraudulent transactions. Traditional fraud detection strategies, which rely mostly on static keyword-based heuristics or predefined rule-based detection, have proven to be less effective against these dynamic and adaptive threats. Therefore, in this paper, we propose a real-time fraud detection model based on fine-tuned large language models (LLMs) to bridge this gap. Unlike conventional systems, the proposed architecture leverages deep contextual understanding, semantic reasoning, and intent classification to identify suspicious interactions in live communication environments. The system integrates several key components: a speech-to-text transcription pipeline for converting voice calls into structured text; a retrieval-augmented generation (RAG) mechanism that incorporates organizational policies and domain-specific knowledge into decision-making; and a feedback loop enabling continuous adaptation to novel fraud strategies. In addition, the framework utilizes a scenario generator to augment the datasets, generating contrastive benign versus malicious dialogue as a means to enhance model robustness. Trained with LoRA and quantization techniques for efficiency reasons, the model performs well on controlled evaluations, reaching over 97% accuracy in predicting the intent of fraudulent messages within three conversational turns. Real-world deployment results demonstrate tangible improvements in incidents related to fraud, enhanced decision support for analysts utilizing outputs from explainable AI, and increased flexibility in responding to new threats. In addition to advancing the technical state of fraud detection research, this work also contributes to the broader research efforts on cybersecurity resiliency by demonstrating the feasibility of operationalizing LLMs for high-stakes real-time applications.

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.

The advent of emerging technologies has transformed the field of bioinformatics, bringing knowledge to a deeper understanding of more intricate diseases. These new paradigms include multi-omics integration, network medicine, predictive genomics, explainable AI, large language models (LLMs), and pan-genome references, which collectively improve the discovery of disease mechanisms and biomarkers. These advancements hold the prospect of enhanced accuracy in diagnostic processes, identification of therapeutic targets, and individualized treatment. Disease etiology could be better understood through the integration of data from genomics, transcriptomics, proteomics, metabolomics, single-cell information, and clinical metadata. Interpretable ML and explainable AI are capable of improving visibility and medical confidence. In the meantime, existing network biology and predictive genomics aid in the modeling of polygenic diseases. This paper summarizes the major trends based on the latest literature, assesses the biomedical potential, and identifies a series of potential issues related to computation, bias, and data integration, as well as the impact of these innovations on the future of precision medicine.