Logical Reasoning Research Articles

Beyond Text Generation: Assessing Large Language Models’ Ability to Reason Logically and Follow Strict Rules

The growing interest in advanced large language models (LLMs) like ChatGPT has sparked debate about how best to use them in various human activities. However, a neglected issue in the debate concerning the applications of LLMs is whether they can reason logically and follow rules in novel contexts, which are critical for our understanding and applications of LLMs. To address this knowledge gap, this study investigates five LLMs (ChatGPT-4o, Claude, Gemini, Meta AI, and Mistral) using word ladder puzzles to assess their logical reasoning and rule-adherence capabilities. Our two-phase methodology involves (1) explicit instructions about word ladder puzzles and rules regarding how to solve the puzzles and then evaluate rule understanding, followed by (2) assessing LLMs’ ability to create and solve word ladder puzzles while adhering to rules. Additionally, we test their ability to implicitly recognize and avoid HIPAA privacy rule violations as an example of a real-world scenario. Our findings reveal that LLMs show a persistent lack of logical reasoning and systematically fail to follow puzzle rules. Furthermore, all LLMs except Claude prioritized task completion (text writing) over ethical considerations in the HIPAA test. Our findings expose critical flaws in LLMs’ reasoning and rule-following capabilities, raising concerns about their reliability in critical tasks requiring strict rule-following and logical reasoning. Therefore, we urge caution when integrating LLMs into critical fields and highlight the need for further research into their capabilities and limitations to ensure responsible AI development.

Development and evaluation of a 4M taxonomy from nursing home staff text messages using a fine-tuned generative language model.

This study aimed to explore the utilization of a fine-tuned language model to extract expressions related to the Age-Friendly Health Systems 4M Framework (What Matters, Medication, Mentation, and Mobility) from nursing home worker text messages, deploy automated mapping of these expressions to a taxonomy, and explore the created expressions and relationships. The dataset included 21357 text messages from healthcare workers in 12 Missouri nursing homes. A sample of 860 messages was annotated by clinical experts to form a "Gold Standard" dataset. Model performance was evaluated using classification metrics including Cohen's Kappa (κ), with κ ≥ 0.60 as the performance threshold. The selected model was fine-tuned. Extractions were clustered, labeled, and arranged into a structured taxonomy for exploration. The fine-tuned model demonstrated improved extraction of 4M content (κ = 0.73). Extractions were clustered and labeled, revealing large groups of expressions related to care preferences, medication adjustments, cognitive changes, and mobility issues. The preliminary development of the 4M model and 4M taxonomy enables knowledge extraction from clinical text messages and aids future development of a 4M ontology. Results compliment themes and findings in other 4M research. This research underscores the need for consensus building in ontology creation and the role of language models in developing ontologies, while acknowledging their limitations in logical reasoning and ontological commitments. Further development and context expansion with expert involvement of a 4M ontology are necessary.

How Students Use Cognitive Structures to Process Information in the Algebraic Reasoning?

Cognitive processes are procedures for using existing knowledge to combine it with new knowledge and make decisions based on that knowledge. This study aims to identify the cognitive structure of students during information processing based on the level of algebraic reasoning ability. This type of research is qualitative with exploratory methods. The data collection technique used began by providing a valid and reliable test instrument for algebraic reasoning abilities for six mathematics education student programs at the Islamic University of Sultan Agung Indonesia. Subjects were selected based on the level of upper, middle, and lower algebraic reasoning abilities. The results showed that (1) students with the highest level of algebraic reasoning ability meet the logical structure of Logical Reasoning which shows that students at the upper level can find patterns and can generalize; (2) Students at the intermediate level understand the cognitive structure of Symbolic Representations, where students can make connections between knowledge and experience and look for patterns and relationships but have difficulty making rules and generalizations; (3) students at lower levels understand the cognitive structure of Comparative Thinking, where students are only able to make connections between prior knowledge and experience.

A Novel Conflict Deduction Algorithm Based on Contradiction Separation Inference Rule

Automated reasoning, a significant field within artificial intelligence, has attracted increased attention in recent years due to the rising demand for trustworthy AI. Binary resolution, among other inference rules, is crucial in automated reasoning of first-order logic, including the new conflict resolution method. Conflict resolution processes only two clauses in each deduction step and eliminates a complementary pairs of literals from input clauses. This paper proposes a contradiction separation conflict deduction (CSCD) method based on the contradiction separation rule to address these limitations. This novel resolution methodology, together with its automated reasoning theory and method, handles several clauses in each deduction step to seek for conflicts and generates learnt clauses through synergized deduction. Thus, the approach improves deduction by detecting conflicts more effectively, especially with lengthier input clauses. CSCD and conflict resolution are analyzed in detail, then how to create a practical CSCD algorithm and its implementation is summarized. We tested the CSCD algorithm to solve the CASC-26 problems and also applied it to the current leading ATP system (Eprover). Experimental results show that the CSCD deduction approach improves reasoning capability of conflict deduction method. Additionally, the Eprover with the proposed CSCD algorithm improves its performance and has solved various problems with a rating of 1 from the benchmark database TPTP.

Study on the Influence of Multiple Derivation Method of General Term Formula of Series on Students' Logical Ability

This paper discusses the influence of multiple derivation method on students' logical reasoning ability. By comparing traditional derivation method with multivariate derivation method, this paper analyzes how the latter can improve students' flexibility and accuracy in solving problems through various strategies such as graphic method, induction method and recurrence method. The research shows that adopting multiple derivation method can strengthen students' logical reasoning ability, enhance the depth and creativity of students' mathematical thinking, and promote students' multi-angle thinking divergence when solving mathematical problems. This method helps students better understand the knowledge of number series, and exercises their rigorous logical thinking and the ability to solve practical problems. It opens up a new teaching idea and operation direction for mathematics teaching.

Logical reasoning for human activity recognition based on multisource data from wearable device

Smart wearable devices detection and recording of people’s everyday activities is critical for health monitoring, helping persons with disabilities, and providing care for the elderly. Most of the research that is being conducted uses a machine learning-based methodology; however, these approaches frequently have issues with high computing resource consumption, burdensome training data gathering, and restricted scalability across many contexts. This research suggests a behaviour detection technology based on multi-source sensing and logical reasoning to address these problems. In order to realize the natural fusion of signal processing and logical reasoning in behavior recognition research, this work designs a lightweight behavior recognition solution using the pertinent theories of ontology reasoning in classical artificial intelligence. Machine learning technology is also employed for behavior recognition using the same data set. Once the best model has been chosen, the cross-person recognition results after testing and modification of parameters are 90.8% and 92.1%, respectively. This technology was used to create a behaviour recognition system, and several tests were run to assess how well it worked. The findings demonstrate that the suggested strategy achieves over 90% recognition accuracy for 11 different daily activities, including jogging, walking, and stair climbing. Additionally, the suggested strategy dramatically minimises the quantity of user-provided training data needed in comparison to machine learning-based behaviour identification techniques.

Forming the value of a healthy lifestyle among students through mathematical problems

Introduction: Mathematical skills are of great importance since they foster critical thinking, problem-solving, and logical reasoning. Mathematical competence focuses on enabling students to apply mathematical concepts in real-life contexts, particularly to form the value of a healthy lifestyle. Objective: To study the possibilities of shaping the student's value of a healthy lifestyle and health-preserving competence through integrating mathematics problems into the educational process.Methods: To achieve the research's aim, experimental research design was applied. The experiment involved 23 instructors from different regions of Ukraine who taught mathematics in the 5th grade. A total of 404 students participated in the study, with 250 forming the Experimental Group and 154 forming the Control Group. The intervention phase lasted 12 weeks and included 7 mathematics topics. The method of descriptive statistics was selected for data analysis.Results: Various teaching strategies are used in the mathematics classroom for the formation of the value of a healthy lifestyle. Students consider video-based activities and problems the most exciting and engaging. At the same time, text activities are found to be less effective in the mathematics classroom. Besides, the experiment demonstrated that students remembered the educational information better when they solved mathematics problems in the classroom and were engaged in active or interactive activities. Using mathematics to form the value of a healthy lifestyle offers several advantages and challenges. Conclusions: The results have significant implications for secondary education improvement and student development

Critical Thinking in Authentic Assessment: An Exploration into Argumentative Writing Non-English Department in Higher Education

This research aims to thoroughly explore how authentic assessment methods, designed to emulate real-life challenges, contribute to enhancing the abilities of students to construct logical arguments, critically evaluate evidence, and articulate thoughts coherently in writing. In order to achieve the stated objective, a qualitative research design was adopted, and content analysis was utilized systematically for the examination of the quality of argument, evaluation of evidence, and logical reasoning in the argumentative writings of the observed students. The results obtained from the data analysis conducted showed that all the arguments were relevant in general discussions and added precision through the use of examples. Accordingly, the examples given provided clear insight into how each application related to the general discussions, hence each example was considered relevant in improving the understanding of the topic in question. In an effort to ensure the conducted analysis was carried out thoroughly, deep essays in the expansive coverage of the details relevant to the different aspects of the research were reviewed. Each of the essays threw forward the central contention or stance taken with strength and the support of quality evidence including concrete examples from life, findings from previous research, and case studies. As a recommendation, future research should be conducted with a specific focus on analyzing critical thinking and argumentation skill development in the students along longitudinal lines, with the primary aim of observing how the skills change with different teaching methodologies, curriculum structures, and educational interventions.

Unraveling the connection: A systematic review of learning styles and mathematics achievement

Mathematics is an essential subject in schools, helping develop cognitive skills such as critical analysis, logical reasoning, and problem-solving. However, academic achievement in mathematics often declines, with some students having difficulty understanding mathematical ideas. Many factors influence mathematics achievement, including students' learning styles. This study aims to identify students' learning styles and how they may affect their academic performance. The study's findings indicate that mathematics often uses visual-spatial learning mode. Understanding mathematical concepts usually requires first seeing shapes and relationships. Schools are advised to train instructors in learning style-based teaching methods because a better understanding of students' learning styles can improve engagement and academic achievement.

Methods Of Using Historical and Scientific Materials in Mathematics Education

Modern society increasingly demands graduates equipped with a deep worldview and a solid foundation of knowledge, skills, and competencies. Throughout their education, students are exposed to the fundamentals of various sciences, including mathematics, for eleven years. Given that mathematics is one of the core subjects in secondary education, it is imperative that students not only master the methods of computation and logical reasoning but also deeply engage with mathematical concepts through historical contexts. This paper explores the integration of historical and scientific materials into mathematics education, emphasizing their significance in enriching the learning experience. By utilizing historical facts and narratives, educators can present mathematics as a dynamic and evolving discipline, fostering a sense of connection between students and the subject matter. The research indicates that the incorporation of historical materials enhances students' conceptual understanding, critical thinking skills, and mathematical modeling abilities. Furthermore, it promotes a broader appreciation for mathematics as an essential component of personal culture and societal development. This study aims to provide educators and prospective students with strategies to leverage historical resources, thereby transforming mathematics into a vibrant field of inquiry. Through this approach, we seek to cultivate a generation of learners who view mathematics not only as a set of abstract concepts but also as a rich, contextualized discipline that reflects human thought and innovation over time. Keywords: History of mathematics, content of historical and scientific materials, geometric methods of solving equations, proof of identities using geometric methods, lune and its area, content requirements, geometric methods of solving equations, proof of identities using geometric methods. AMS Subject Classification: 97E50 - Mathematics education, 97C30 - Curriculum and pedagogy in mathematics, 97D40 - Teaching methods and instructional strategies, 01A30 - History of mathematics, 97K10 - Use of technology in teaching mathematics.

The Eloquence of Argumentationand Its Impact on Critical Thinking in Al-Sijlmassi: "A Study on the Branching and Evolution of Terminology"

Objective:The study aims to explore the rhetoric of argumentation by enriching the critical and rhetorical heritage with insights that reveal the dynamics of influence and interaction across cultures that have synergized to enhance criticism and rhetoric. These insights also contribute to the development of relevant terminology, as philosophical thought and logical reasoning were among the most significant influences in this heritage. Methodology:It is well-known to specialists that argumentation emerges at a later stage of composition, as it leverages pragmatics as a driving force to achieve its purpose. Therefore, the study focuses on examining the relationships within argumentation and some of its branches, aiming to uncover the logical and philosophical forces utilized by Al-Sijilmassi in refining and regulating his terminology. Significance:The importance of this study lies in the fact that it addresses an independent field of knowledge that has sparked debates among scholars and linguists for centuries. It seeks to prepare the audience’s mind for the constructed rhetorical event and challenge pre-existing mental influences. The importance of argumentation lies in understanding the rhetorical techniques employed by the sender, which rendered the message acceptable to the audience. Indeed, argumentation as a theory was developed within the realms of logic, philosophy, and pragmatic linguistics. Summary and Results: This study deals with a phenomenon that reveals the evolution of terminology and the mechanisms of argumentation that contributed to its production. Therefore, it requires thorough examination to uncover its diverse forms in light of the historical development of terminology over the centuries.

Logics for Strategic Reasoning about Socially Interacting Rational Agents

Logics for Strategic Reasoning about Socially Interacting Rational Agents

PROMOTING ALGORITHMIC THINKING THROUGH UNPLUGGED PRIMARY SCIENCE ACTIVITY IN RURAL SCHOOLS

Algorithmic thinking, a method for solving problems through a step-by-step process that leads to a solution, is an essential component of computational thinking. Combining computational thinking and artificial intelligence (AI) in rural areas through unplugged activities provides an innovative approach to enhance science inquiry education. This article proposed the integration of algorithmic thinking and artificial intelligence (AI) within rural primary science education through hands-on, unplugged activities. Recognizing the challenges posed by limited digital access in these areas, the study introduces a model that encourages young learners to participate in STEM inquiries using practical, algorithm-oriented tasks that require little to no technology. This method promotes critical thinking, problem-solving skills, and scientific exploration by aligning with Piaget’s stages of cognitive development, allowing students to interact with materials and engage in practical scenarios. Furthermore, the research emphasizes how algorithmic thinking enhances logical reasoning and STEM literacy. By incorporating interactive games such as “Algorithm Walk” and “Science Sorting Relay,” the proposed model offers a contextually relevant and cost-effective approach to integrating computational thinking and fundamental AI concepts into primary education, effectively preparing students for future careers in science and technology. This would help in developing more customized, effective educational strategies and policies aimed at truly elevating meaningful educational experiences.

AI-Driven Sentiment Classification via Combinatorial Techniques and Reasoning

This paper proposes an AI-driven approach to sentiment analysis, leveraging mathematical concepts such as permutations, along with logical reasoning techniques. The method involves splitting the text; permutations are used to extract n-grams. AI-driven logic is then applied for feature scoring. Finally, fuzzy logic integrates these scores to classify sentiments. This approach focuses on enhancing sentiment classification accuracy by blending AI-based features.

Система образования в российской Арктике: результаты оптимизации и приоритеты развития

Education forms the foundation of social development, improves quality of life, and supports the creation of sustainable communities. It does so by delivering essential services, fostering territorial cohesion and social integration, developing human and social capital, stimulating economic growth, and laying the groundwork for higher income and better employment opportunities. Additionally, it boosts competitiveness and productivity. Ensuring access to quality primary education at the place of residence, along with equitable opportunities for vocational training and higher education, is critical for the sustainable development of the Arctic territories. This study contributes to the scientific discourse on the development of human resources and educational infrastructure in the Russian Arctic, continuing the author’s publication series on the social infrastructure of the Arctic. The article aims to examine changes in human resources and infrastructure within the education system of the Russian Arctic over the past two decades and to propose directions for its further development. The research employs methods such as content analysis, logical reasoning, and comparative analysis. Findings indicate that, in recent years, the education sector in the Russian Arctic has undergone optimization through mergers and closures of institutions and reductions in personnel, leading to increased polarization in the sector. Addressing these challenges requires policy improvements to ensure access to quality primary education not only in urban centers but also in sparsely populated Arctic areas. There is also a need to expand vocational training opportunities directly within Arctic regions, codify existing initiatives, and integrate them with new educational projects and programs. The practical significance of this research lies in its potential application in public administration for advancing the education system in the Russian Arctic. Future research in this area should focus on in-depth analyses of international practices, studies of wages and the private education sector, and evaluations of the quality of educational programs.

A Review of Large Language Models: Fundamental Architectures, Key Technological Evolutions, Interdisciplinary Technologies Integration, Optimization and Compression Techniques, Applications, and Challenges

Large language model-related technologies have shown astonishing potential in tasks such as machine translation, text generation, logical reasoning, task planning, and multimodal alignment. Consequently, their applications have continuously expanded from natural language processing to computer vision, scientific computing, and other vertical industry fields. This rapid surge in research work in a short period poses significant challenges for researchers to comprehensively grasp the research dynamics, understand key technologies, and develop applications in the field. To address this, this paper provides a comprehensive review of research on large language models. First, it organizes and reviews the research background and current status, clarifying the definition of large language models in both Chinese and English communities. Second, it analyzes the mainstream infrastructure of large language models and briefly introduces the key technologies and optimization methods that support them. Then, it conducts a detailed review of the intersections between large language models and interdisciplinary technologies such as contrastive learning, knowledge enhancement, retrieval enhancement, hallucination dissolution, recommendation systems, reinforcement learning, multimodal large models, and agents, pointing out valuable research ideas. Finally, it organizes the deployment and industry applications of large language models, identifies the limitations and challenges they face, and provides an outlook on future research directions. Our review paper aims not only to provide systematic research but also to focus on the integration of large language models with interdisciplinary technologies, hoping to provide ideas and inspiration for researchers to carry out industry applications and the secondary development of large language models.

Management accounting and reporting as a tool for improving the efficiency of educational organizations

Subject. This article deals with the issues of methodology and organization of the management accounting and reporting system in Russian educational organizations. Objectives. The article aims to reveal the possibilities of management accounting tools in improving the quality of management of educational organizations, as well as motivating the activities of both structural divisions and individual employees. Methods. For the study, I used a systems approach, comparison, systematization, generalization of data, as well as the methods of logical generalization and system reasoning. Results. The article presents the results of a rapid analysis of management accounting in foreign universities and offers an algorithm for building a management accounting system in Russian educational organizations. Based on the SWOT analysis of strategic planning, the article reveals its advantages, identifies strengths and weaknesses, opportunities and existing threats inherent in educational activities. The article also presents the developed algorithm for the implementation of the system of key indicators and reveals their specifics in relation to educational activities. Due to the lack of institutional regulation of management accounting in Russia, the article also proposes a system of bylaws that helps arrange a system of management accounting in educational organizations. Conclusions. The considered management accounting tools can significantly improve the quality of management of an educational organization. A management accounting system will help an educational organization accumulate financial and non-financial information from internal and external sources, properly detail it and present it to decision-makers. The development of management accounting strategies is an important trend.

Helen Verran and the Question of African Logic

Hitherto, the African intellect had been decimated by notable European scholars such as David Hume, Charles Darwin, Friedrich Hegel, Lucien Levy-Bruhl to name a few. The common denominator among these male scholars is that the African intellect is not yet developed to the extent that it can accommodate logical reasoning. Whereas notable African scholars have responded to these charges as misleading whilst exploring ways of coming up with a logic system that can mediate the theory, thought and practice peculiar to Africans yet applicable in other climes, the role of women in this journey has usually been downplayed. This research thereby seeks to fill this void by making a case for the contribution of the Australian Helen Verran who did not engage in armchair scholarship as most of her European male counterparts who deny the African the ability to reason logically, but journeyed to Nigeria to perform some experiments with the Yorùbá numerical system. She is persuaded that through the traditional Yorùbá numerical pattern, an underlying logic system is implied. Even when her conclusions are questionable on several fronts, this research concludes that her role in instilling confidence in the development of artificial logic in Africa must not go unmentioned.

Moderation and Envisioned Civilization: The Interplay Between Rationality, Morality, Spirituality

The triumph of Western civilization which marked bysignificant industrial revolution through scientific breakthroughs andtechnological advancements still not necessarily make this civilizationbetter as expected. With strongly emphasis on its pursuit ofrationality, this civilization has faced criticism from numerousexperts due to its various deficiencies and subsequent detrimentalconsequences. This article will investigate on how the notion of"envisioned civilization" can be realized by starting the process of itsformation on the principle of moderation. The existence ofmoderation in the context of envisioning a civilization lies whencivilization is driven by synthesizing Rationality, Morality andSpirituality in a balanced manner and taking roles for each other.Based on interdisciplinary approach, the study examines how theseamless incorporation of logical reasoning, ethical standards, andspiritual beliefs might enhance the development of a well-roundedand enlightened social structure. The findings demonstrate that byintegrating these three dimensions harmoniously can support thelimitation of rationality aspect, establishing a more comprehensivecivilization

The Importance of the World Oil and Gas Industry in The Economy of Countries

The oil and gas industry is a cornerstone of the global economy, driving energy production, industrial development, and international trade. This study explores the industry’s critical role in economic growth, its production trends, resource reserves, and challenges. The research methodology includes a review of foreign literature and an analysis of official statistical data through comparative and logical reasoning techniques. Results highlight the significant contributions of oil and gas to energy generation, the chemical industry, and economic stability, with over 50% of global energy needs met by these resources. However, challenges such as environmental impacts, finite reserves, and competition from renewable energy sources pose risks to sustainability. Innovative technologies, environmental reforms, and strategic geopolitical actions are identified as solutions to ensure the industry’s future. This study underscores the need for global collaboration and innovation to balance resource utilization with environmental stewardship. The article investigates the oil and gas industry, which is considered one of the priority sectors for the country's economy, its problems, innovations, production trends, resource reserves, etc. In particular, the role of the oil and gas industry in the economies of countries, the economic potential and the process of increasing the efficiency of resource use are analyzed.