Leveraging large language models for enhanced simulation-based learning in police and law enforcement

The article analyzes the peculiarities of professional training of law enforcement officers. The relevance of the specific functions of the state in the professional training of domestic law enforcement officers is revealed, which is due to the specifics of the activities of officials and other officials of law enforcement agencies, called to ensure the interests of citizens, society and the state. Doctrinal opinions on the professional training of law enforcement officers were analyzed, as well as a number of legislative and sub-legislative legal acts were studied, including the Laws of Ukraine: «On Civil Service», «On the National Police», «On Social and Legal Protection of Servicemen and Their Family Members» , orders of the Ministry of Internal Affairs of Ukraine on the organization of initial professional training of police officers, who are first accepted for police service, on higher educational institutions of the Ministry of Internal Affairs, regulating the legal relationship of professional training of law enforcement officers. It is emphasized that an important role in the law enforcement activity of a law enforcement officer is played by his professional competence, personal positive human qualities that influence his formation as a personality. The opinion expressed is that the professional activity of a law enforcement officer is inseparable from his professional competence. A theoretical definition of the concept of «professional competence» is given as a set of acquired and necessary professional knowledge, abilities and practical skills that, depending on the field of professional activity, a law enforcement officer can perform within the limits of the powers determined by the position in accordance with the law and other regulatory legal acts. It is justified that every law enforcement officer should be a highly cultured person, have a high level of legal culture, tolerance, and humanity.It was concluded that the law enforcement function belongs to one of the most important functions of the social legal state and covers the entire complex of internal and external functions of the state enshrined in the Constitution and laws of Ukraine, each of which affects the activity of the state-authorized law enforcement body in accordance with the purpose and tasks of its activity. A necessary condition for the implementation of tasks and the implementation of internal and external functions of the state requires proper provision of law enforcement bodies with material resources, financial and monetary support, a guarantee of social protection, and determination of the powers of the law enforcement body. The implementation of the law enforcement function is inextricably linked with the activities of the law enforcement body, its officials and officials. This function is objectified and developed as an integrated indicator of professional competence, possession of organizational, special and legal knowledge and entrusts the state with the important function of providing professional training and special training of the future highly qualified specialist – a law enforcement officer who has mastered the relevant theoretical knowledge and practical skills, who psychologically ready to act in extreme conditions, be able to and know how to use acquired knowledge in order to ensure the protection of human and citizen rights and freedoms, legal order and state security.

How Can <i>IJDS</i> Authors, Reviewers, and Editors Use (and Misuse) Generative AI?

The purpose of the study was to substantiate the effectiveness of hand-to-hand combat as a service-applied sport in the process of physical training of law enforcement officers. Materials and methods. Theoretical analysis of scientific and methodical literature, generalization of scientific data of modern approaches to the organization of the process of special physical training of law enforcement officers, pedagogical observations and pedagogical experiment were used. To determine the operational composition of technical and tactical actions used by law enforcement officers in their professional activities and differences in martial arts on various grounds, an analysis of video materials of competitions among law enforcement agencies in hand-to-hand combat from the section "Demonstrations of applied equipment" of hand-to-hand combat in 2019-2020 was used. Results and discussion. The use of hand-to-hand combat - service-applied sport as an element of special physical training of law enforcement officers is substantiated. It is established that the distinguishing feature of hand-to-hand combat as a sport and part of special physical training of law enforcement officers is the presence of directions of work with weapons (stick, knife, pistol, machine gun), counteraction to several attackers and the use of an element of surprise (unexpected attack). The operational composition of the means used by law enforcement officers in their professional activities and athletes in different types of martial arts and the differences between the types of martial arts by different distinctions are determined. Conclusion. Hand-to-hand combat is a unique service-applied sport, which consists of sections "Demonstration of applied equipment" and "Duels". A distinctive feature of hand-to-hand combat as a sport and part of special physical training of law enforcement officers is the presence of areas of work with weapons (stick, knife, pistol, machine gun), resistance to several attackers and the use of an element of surprise (unexpected attack). The content of competitive activity in the section "Demonstration of applied equipment" of hand-to-hand combat fully corresponds to the specifics of solving operational and service tasks without the use and with the use of weapons by law enforcement officers. The operational composition of the means used by law enforcement officers in their professional activities and athletes in various martial arts (hand-to-hand combat, combat sambo, pankration) are identical, which in turn allows in the process of special physical training of law enforcement officers to conduct classes in these martial arts. According to the main features that distinguish different types of martial arts (clothing, allowed and prohibited by law ways to achieve advantage, the position in which to fight, the size and features of the site, the time allotted for technical and tactical actions) hand-to-hand combat is most suitable for special physical training, training of law enforcement officers. It is proved that hand-to-hand combat is the most suitable type of martial arts for special physical training of law enforcement officers

The article examines the use of the CrossFit system as a means of health fitness training in vocational and applied physical training of future law enforcement officers. It was found that CrossFit training complexes should be designed taking into account the level of physical fitness of cadets and must be included in the content of physical training classes for law enforcement officers. CrossFit develops in a balanced way all the components of physical fitness of an individual including cardio-respiratory endurance, performance, strength, flexibility, speed, power, coordination, accuracy, balance, and agility. An experimental program based on cross-fit exercises was presented, which consisted of five blocks. It was pointed out that vocational and applied physical training of law enforcement officers (military officers, firefighters, and officers of various law enforcement agencies) in the United States, Canada, Europe is carried out using health fitness training, in particular the CrossFit system.

Ongoing assessments in a course are crucial for tracking student performance and progress. However, generating and evaluating tests for each lesson and student can be time-consuming. Existing models for generating and evaluating question-answer pairs have had limited success. In recent years, large language models (LLMs) have become available as a service, offering more intelligent answering and evaluation capabilities. This research aims to leverage LLMs for generating questions, model answers, and evaluations while providing valuable feedback to students and decentralizing the dependency on faculty.We finetune existing LLMs and employ prompt engineering to direct the model toward specific tasks using different generative agents. One agent generates questions, another generates answers, and the third takes the human answers to evaluate and ensure the quality. Human evaluation is conducted through focus group analysis, and student progress and faculty feedback are tracked. Results demonstrate the potential of LLMs to provide automatic feedback and learning progress tracking for both students and faculty.In conclusion, this paper demonstrates the versatility of LLMs for various learning tasks, including question generation, model answer generation, and evaluation, all while providing personalized feedback to students. By identifying and addressing knowledge gaps, LLMs can support continuous evaluation and help students improve their understanding before semester exams. Furthermore, knowledge gaps from students identified by the agent can be highlighted and addressed through additional classes or support materials, potentially generated by the same model, leading to a more personalized learning experience.

Introduction: according to the official statistics, the number of acts involving information technology is increasing every year in Russia. In particular, currently, the types of crimes in the field of information technology are changing qualitatively and continue to evolve continuously, becoming highly organized and more sophisticated. Through the use of information technologies in Russia, such crimes as hacking, illegal data acquisition (information espionage), theft of other people’s property from payment (settlement) cards and accounts of citizens, trafficking of drugs, arms, human beings are committed; the extremist literature is distributed, new members of terrorist groups are recruited; pornography, including children, is spread, illegal gambling and online games are conducted; fraud through the use of cellular and IP-telephony services, theft of personal data in large amount and selling them, and other crimes are committed using information technologies. The current type of computer fraud – phishing – is gaining momentum. Its essence is that cybercriminals seek to get hold of the data of ordinary people through computer technology, and using this data, get hold of their funds, including financial ones. It seems that such actions can neither contribute to the development of Russian society, nor to the development of civilized relations in society, nor to the development of information networks themselves. After all, any technology can be used for both constructive and non-constructive technologies. And when these goals are destructive, the law enforcement agencies, in our opinion, should have an effective level of training to deal with such violations. We believe that it is not enough to calculate, detect, and establish. We still need to be able to bring the culprit to criminal responsibility. In this regard, the most important thing is to ensure that anonymity not only creates the illusion of impunity, but also that the law enforcement agencies have a sufficient legal, organizational and, first of all, personnel basis to expose the criminal. In order to successfully thwart crimes in the field of information technology, the availability of implementation of the adopted standards and the key to the implementation of the state policy in the field of information security is the training and education of appropriate personnel who would provide “breakthrough” results in this area. The purpose of the research is to study the issues of improving the training of the law enforcement officers in countering crimes committed through the use of information technologies. Methods: the research uses a comparative analysis and generalization of the examples of the educational methods used in the educational organizations of the Ministry of Internal Affairs in the field of information security. The authors study, in particular, the general theoretical and practical orientation of the educational process in this area, synthesizing the results obtained, whose purpose is to improve the training of highly qualified specialists for the Internal Affairs bodies capable of countering crimes in the field of information technologies. Results: the authors formulate the main directions for improving the training of the law enforcement officers to counter crimes committed using information technologies, in particular, on the example of the educational organizations used in the educational process of the Ministry of Internal Affairs of Russia. Thus, one of the measures proposed by the authors in this direction is the opening of a new specialty – cyber-investigator or cyber-criminalist. The entry of developed countries into the sixth technological order and the further active digitalization of the world economy predict a huge scale and replication of crimes using information technologies. This circumstance actualizes the need to popularize the profession of a cyber-investigator – a specialist with an interdisciplinary education, i.e. experience in the investigative agencies will have to be combined with the skills of a criminalist and a specialist in the field of information protection.

Large language models (LLMs) have grown rapidly in size and capabilities as more training data and compute power has become available. Since the release of ChatGPT in late 2022, there has been growing interest and exploration around potential applications of LLM technology. Numerous examples and pilot studies demonstrating the capabilities of these tools have emerged across several domains. For rheumatology professionals and patients, LLMs have the potential to transform current practices in medicine. Recent studies have begun exploring capabilities of LLMs that can assist rheumatologists in clinical practice, research, and medical education, though applications are still emerging. In clinical settings, LLMs have shown promise in assist healthcare professionals enabling more personalized medicine or generating routine documentation like notes and letters. Challenges remain around integrating LLMs into clinical workflows, accuracy of the LLMs and ensuring patient data confidentiality. In research, early experiments demonstrate LLMs can offer analysis of datasets, with quality control as a critical piece. Lastly, LLMs could supplement medical education by providing personalized learning experiences and integration into established curriculums. As these powerful tools continue evolving at a rapid pace, rheumatology professionals should stay informed on how they may impact the field.

ABSTRACTThe overwhelming success of GPT‐4 in early 2023 highlighted the transformative potential of large language models (LLMs) across various sectors, including national security. This article explores the implications of LLM integration within national security contexts, analysing their potential to revolutionise information processing, decision‐making and operational efficiency. Whereas LLMs offer substantial benefits, such as automating tasks and enhancing data analysis, they also pose significant risks, including hallucinations, data privacy concerns, and vulnerability to adversarial attacks. Through their coupling with decision‐theoretic principles and Bayesian reasoning, LLMs can significantly improve decision‐making processes within national security organisations. Namely, LLMs can facilitate the transition from data to actionable decisions, enabling decision‐makers to quickly receive and distill available information with less manpower. Current applications within the US Department of Defense and beyond are explored, for example, the USAF's use of LLMs for wargaming and automatic summarisation, that illustrate their potential to streamline operations and support decision‐making. However, these applications necessitate rigorous safeguards to ensure accuracy and reliability. The broader implications of LLM integration extend to strategic planning, international relations and the broader geopolitical landscape, with adversarial nations leveraging LLMs for disinformation and cyber operations, emphasising the need for robust countermeasures. Despite exhibiting “sparks" of artificial general intelligence, LLMs are best suited for supporting roles rather than leading strategic decisions. Their use in training and wargaming can provide valuable insights and personalised learning experiences for military personnel, thereby improving operational readiness.

Large Language Models (LLMs) notably GPT-4, demonstrate exceptional language generation and comprehension abilities, and they have potential uses in clinical practice, learning, and medical research. In this study, we explore practical use of Large Language Models (LLMs) in enhancing case-based learning in medical education. The study employes a designed mixed-methods approach, combining quantitative metrics with qualitative feedback from 100 medical students, providing comprehensive insights into both the technical performance and educational value of LLM-based feedback systems. Our results indicate that LLMs can enhance medical students’ History and Physical (H&amp;P) skills by providing personalized insights, fostering critical thinking, and improving their abilities to analyze, diagnose, and present clinical cases. This study has surfaced significant insights into the potential benefits and limitations of integrating LLMs into medical education. Our findings show the positive impact of LLMs on enhancing personalized learning experiences, critical thinking, and the effectiveness of case-based learning aids and highlighting its limitations.

The aging population presents an accomplishment for society but also poses significant challenges for governments, health care systems, and caregivers. Elevated rates of functional limitations among older adults, primarily caused by chronic conditions, necessitate adequate and safe care, including in-home settings. Traditionally, informal caregiver training has relied on verbal and written instructions. However, the advent of digital resources has introduced videos and interactive platforms, offering more accessible and effective training. Large language models (LLMs) have emerged as potential tools for personalized information delivery. While LLMs exhibit the capacity to mimic clinical reasoning and support decision-making, their potential to serve as alternatives to evidence-based professional instruction remains unexplored. We aimed to evaluate the appropriateness of home care instructions generated by LLMs (including GPTs) in comparison to a professional gold standard. Furthermore, it seeks to identify specific domains where LLMs show the most promise and where improvements are necessary to optimize their reliability for caregiver training. An observational, comparative case study evaluated 3 LLMs-GPT-3.5, GPT-4o, and Microsoft Copilot-in 10 home care scenarios. A rubric assessed the models against a reference standard (gold standard) created by health care professionals. Independent reviewers evaluated variables including specificity, clarity, and self-efficacy. In addition to comparing each LLM to the gold standard, the models were also compared against each other across all study domains to identify relative strengths and weaknesses. Statistical analyses compared LLMs performance to the gold standard to ensure consistency and validity, as well as to analyze differences between LLMs across all evaluated domains. The study revealed that while no LLM achieved the precision of the professional gold standard, GPT-4o outperformed GPT-3.5, and Copilot in specificity (4.6 vs 3.7 and 3.6), clarity (4.8 vs 4.1 and 3.9), and self-efficacy (4.6 vs 3.8 and 3.4). However, the models exhibited significant limitations, with GPT-4o and Copilot omitting relevant details in 60% (6/10) of the cases, and GPT-3.5 doing so in 80% (8/10). When compared to the gold standard, only 10% (2/20) of GPT-4o responses were rated as equally specific, 20% (4/20) included comparable practical advice, and just 5% (1/20) provided a justification as detailed as professional guidance. Furthermore, error frequency did not differ significantly across models (P=.65), though Copilot had the highest rate of incorrect information (20%, 2/10 vs 10%, 1/10 for GPT-4o and 0%, 0/0 for GPT-3.5). LLMs, particularly GPT-4o subscription-based, show potential as tools for training informal caregivers by providing tailored guidance and reducing errors. Although not yet surpassing professional instruction quality, these models offer a flexible and accessible alternative that could enhance home safety and care quality. Further research is necessary to address limitations and optimize their performance. Future implementation of LLMs may alleviate health care system burdens by reducing common caregiver errors.

ObjectivesArtificial intelligence (AI) represents an exciting and evolving technology that is increasingly being utilized across pain medicine. Large language models (LLMs) are one type of AI that has become particularly popular. Currently, there is a paucity of literature analyzing the impact that AI may have on trainee education. As such, we sought to assess the benefits and pitfalls that AI may have on pain medicine trainee education. Given the rapidly increasing popularity of LLMs, we particularly assessed how these LLMs may promote and hinder trainee education through a pilot quality improvement project.Materials and MethodsA comprehensive search of the existing literature regarding AI within medicine was performed to identify its potential benefits and pitfalls within pain medicine. The pilot project was approved by UPMC Quality Improvement Review Committee (#4547). Three of the most commonly utilized LLMs at the initiation of this pilot study – ChatGPT Plus, Google Bard, and Bing AI – were asked a series of multiple choice questions to evaluate their ability to assist in learner education within pain medicine.ResultsPotential benefits of AI within pain medicine trainee education include ease of use, imaging interpretation, procedural/surgical skills training, learner assessment, personalized learning experiences, ability to summarize vast amounts of knowledge, and preparation for the future of pain medicine. Potential pitfalls include discrepancies between AI devices and associated cost‐differences, correlating radiographic findings to clinical significance, interpersonal/communication skills, educational disparities, bias/plagiarism/cheating concerns, lack of incorporation of private domain literature, and absence of training specifically for pain medicine education. Regarding the quality improvement project, ChatGPT Plus answered the highest percentage of all questions correctly (16/17). Lowest correctness scores by LLMs were in answering first‐order questions, with Google Bard and Bing AI answering 4/9 and 3/9 first‐order questions correctly, respectively. Qualitative evaluation of these LLM‐provided explanations in answering second‐ and third‐order questions revealed some reasoning inconsistencies (e.g., providing flawed information in selecting the correct answer).ConclusionsAI represents a continually evolving and promising modality to assist trainees pursuing a career in pain medicine. Still, limitations currently exist that may hinder their independent use in this setting. Future research exploring how AI may overcome these challenges is thus required. Until then, AI should be utilized as supplementary tool within pain medicine trainee education and with caution.

Large language models (LLMs) are artificial intelligence (AI) based computational models designed to understand and generate human like text. With billions of training parameters, LLMs excel in identifying intricate language patterns, enabling remarkable performance across a variety of natural language processing (NLP) tasks. After the introduction of transformer architectures, they are impacting the industry with their text generation capabilities. LLMs play an innovative role across various industries by automating NLP tasks. In healthcare, they assist in diagnosing diseases, personalizing treatment plans, and managing patient data. LLMs provide predictive maintenance in automotive industry. LLMs provide recommendation systems, and consumer behavior analyzers. LLMs facilitates researchers and offer personalized learning experiences in education. In finance and banking, LLMs are used for fraud detection, customer service automation, and risk management. LLMs are driving significant advancements across the industries by automating tasks, improving accuracy, and providing deeper insights. Despite these advancements, LLMs face challenges such as ethical concerns, biases in training data, and significant computational resource requirements, which must be addressed to ensure impartial and sustainable deployment. This study provides a comprehensive analysis of LLMs, their evolution, and their diverse applications across industries, offering researchers valuable insights into their transformative potential and the accompanying limitations.

Introduction. The paper aims to find practical aspects of initial professional training in technical and tactical techniques of ground hand-to-hand combat in the context of law enforcement. Materials and methods. The study involves reviewing numerous abstracts of papers focusing on self-defense and various types of martial arts. A comparative analysis of the rules of various sports that are of applied value for the training of law enforcement officers and that embrace groundwork is performed. The questionnaire and pedagogical testing are employed to identify the main tactics and techniques of the initial training in ground hand-to-hand combat, and their variety. The study has determined the specific features of the initial professional training in ground hand-to-hand combat. Research result. The findings have indicated the current degree of the issue coverage and its relevance. The main (basic) technical and tactical methods for initial training of law enforcement officers have been identified using the Brazilian jiujitsu techniques as an example, and their variety has been briefly described. The specific features of initial training in ground fighting for law enforcement officers have been formulated given the features of their professional activities. Conclusion. The relevance of studying and developing positional combat (part of practical hand-to-hand fighting) as one of the areas of professional training of law enforcement officers for the modern realities of one-on-one street fighting, i.e., ground hand-to hand combat, has been determined. The data obtained allows supplementing the theory and methodology of martial arts with new knowledge.

This work presents the development of NOVA, an educational virtual assistant designed for the Parallel Computing course, built using a Retrieval-Augmented Generation (RAG) architecture combined with Large Language Models (LLMs). The assistant operates entirely in Spanish, supporting native-language learning and increasing accessibility for students in Latin American academic settings. It integrates vector and relational databases to provide an interactive, personalized learning experience that supports the understanding of complex technical concepts. Its core functionalities include the automatic generation of questions and answers, quizzes, and practical guides, all tailored to promote autonomous learning. NOVA was deployed in an academic setting at Universidad Politécnica Salesiana. Its modular architecture includes five components: a relational database for logging, a vector database for semantic retrieval, a FastAPI backend for managing logic, a Next.js frontend for user interaction, and an integration server for workflow automation. The system uses the GPT-4o mini model to generate context-aware, pedagogically aligned responses. To evaluate its effectiveness, a test suite of 100 academic tasks was executed—55 question-and-answer prompts, 25 practical guides, and 20 quizzes. NOVA achieved a 92% excellence rating, a 21-second average response time, and 72% retrieval coverage, confirming its potential as a reliable AI-driven tool for enhancing technical education.

Massive Open Online Courses (MOOCs) lack direct interaction between learners and instructors, making it challenging for learners to understand new knowledge concepts. Recently, learners have increasingly used Large Language Models (LLMs) to support them in acquiring new knowledge. However, LLMs are prone to hallucinations which limits their reliability. Retrieval-Augmented Generation (RAG) addresses this issue by retrieving relevant documents before generating a response. However, the application of RAG across different MOOCs is limited by unstructured learning material. Furthermore, current RAG systems do not actively guide learners toward their learning needs. To address these challenges, we propose a Graph RAG pipeline that leverages Educational Knowledge Graphs (EduKGs) and Personal Knowledge Graphs (PKGs) to guide learners to understand knowledge concepts in the MOOC platform CourseMapper. Specifically, we implement (1) a PKG-based Question Generation method to recommend personalized questions for learners in context, and (2) an EduKG-based Question Answering method that leverages the relationships between knowledge concepts in the EduKG to answer learner selected questions. To evaluate both methods, we conducted a study with 3 expert instructors on 3 different MOOCs in the MOOC platform CourseMapper. The results of the evaluation show the potential of Graph RAG to empower learners to understand new knowledge concepts in a personalized learning experience.