We introduce AI University (AI-U), a flexible framework for AI-driven course content delivery that adapts to instructors' teaching styles. At its core, AI-U fine-tunes a large language model (LLM) with retrieval-augmented generation (RAG) to generate instructor-aligned responses from lecture videos, notes, and textbooks. Using a graduate-level finite-element-method (FEM) course as a case study, we present a scalable pipeline to systematically construct training data, fine-tune an open-source LLM with Low-Rank Adaptation (LoRA), and optimize its responses through RAG-based synthesis. Our evaluation - combining cosine similarity, LLM-based assessment, and expert review - demonstrates strong alignment with course materials. We also have developed a prototype web application, available at https://my-ai-university.com, that enhances traceability by linking AI-generated responses to specific sections of the relevant course material and time-stamped instances of the open-access video lectures. Our expert model is found to have greater cosine similarity with a reference on 86% of test cases. An LLM judge also found our expert model to outperform the base Llama 3.2 model approximately four times out of five. AI-U offers a scalable approach to AI-assisted education, paving the way for broader adoption in higher education. Here, our framework has been presented in the setting of a class on FEM - a subject that is central to training PhD and Master students in engineering science. However, this setting is a particular instance of a broader context: fine-tuning LLMs to research content in science.

The availability and abundance of GenAI tools to administer tasks traditionally managed by people have raised concerns, particularly within the education and academic sectors, as some students may highly rely on these tools to complete the assignments designed to enable learning. This article focuses on informing students about the significance of investing their time during their studies on developing essential life-long learning skills using their own critical thinking, rather than depending on AI models that are susceptible to misinformation, hallucination, and bias. As we transition to an AI-centric era, it is important to educate students on how these models work, their pitfalls, and the ethical concerns associated with feeding data to such tools. Keywords: GenAI in Academic Writing GenAI's Ethics GenAI's Privacy Concerns. 1 Introduction Writing academic reports, and papers have been instrumental to assisting students and researchers in shaping their ideas, organising their methods, and practicing their communication skills, particularly when this process is combined with receiving constant feedback from experts. With the launch of OpenAI's first publicly available Large Language Model, namely ChatGPT (GPT-3.5), a significant concern rose within the academic and research community about the reliability of the academic and research output. Evidence suggests that as individuals began discovering the availability and efficiency in using Generative Artificial Intelligence tools in late 2022, there was a significant surge in retracted research articles resulting in more than 10,000 retracted papers [1]. The over-reliance of individuals on various Generative Artificial Intelligence (Gen AI) tools for completing tasks that require a human's critical thinking has raised concerns.

As Large Language Models (LLMs) more deeply integrate into human life across various regions, aligning them with pluralistic cultures is crucial for improving user experience and mitigating cultural conflicts. Existing approaches develop culturally aligned LLMs primarily through fine-tuning with massive carefully curated culture-specific corpora. Nevertheless, inspired by culture theories, we identify two key challenges faced by these datasets: (1) Representativeness: These corpora fail to fully capture the target culture's core characteristics with redundancy, causing computation waste; (2) Distinctiveness: They struggle to distinguish the unique nuances of a given culture from shared patterns across other relevant ones, hindering precise cultural modeling. To handle these challenges, we introduce CAReDiO, a novel cultural data construction framework. Specifically, CAReDiO utilizes powerful LLMs to automatically generate cultural conversation data, where both the queries and responses are further optimized by maximizing representativeness and distinctiveness. Using CAReDiO, we construct a small yet effective dataset, covering five cultures, and compare it with several recent cultural corpora. Extensive experiments demonstrate that our method generates more effective data and enables cultural alignment with as few as 100 training samples, enhancing both performance and efficiency.

As LLMs grow in capability, the task of supervising LLMs becomes more challenging. Supervision failures can occur if LLMs are sensitive to factors that supervisors are unaware of. We investigate Mechanistic Anomaly Detection (MAD) as a technique to augment supervision of capable models; we use internal model features to identify anomalous training signals so they can be investigated or discarded. We train detectors to flag points from the test environment that differ substantially from the training environment, and experiment with a large variety of detector features and scoring rules to detect anomalies in a set of "quirky" language models. We find that detectors can achieve high discrimination on some tasks, but no detector is effective across all models and tasks. MAD techniques may be effective in low-stakes applications, but advances in both detection and evaluation are likely needed if they are to be used in high stakes settings. Large language models (LLMs) excel at a wide range of tasks, yet as their capabilities grow, ensuring effective human oversight becomes increasingly challenging. These considerations have motivated Mechanistic Anomaly Detection (MAD): instead of attempting to understand all facets of a model's internal reasoning, MAD focuses on extracting a signal that indicates when an episode is anomalous--flagging behaviors that deviate from the expected patterns without assuming specific trigger mechanisms (Christiano, 2022). This signal could be used to filter out anomalous episodes, or to trigger deeper investigation.

Estimating item difficulty through field-testing is often resource-intensive and time-consuming. As such, there is strong motivation to develop methods that can predict item difficulty at scale using only the item content. Large Language Models (LLMs) represent a new frontier for this goal. The present research examines the feasibility of using an LLM to predict item difficulty for K-5 mathematics and reading assessment items (N = 5170). Two estimation approaches were implemented: (a) a direct estimation method that prompted the LLM to assign a single difficulty rating to each item, and (b) a feature-based strategy where the LLM extracted multiple cognitive and linguistic features, which were then used in ensemble tree-based models (random forests and gradient boosting) to predict difficulty. Overall, direct LLM estimates showed moderate to strong correlations with true item difficulties. However, their accuracy varied by grade level, often performing worse for early grades. In contrast, the feature-based method yielded stronger predictive accuracy, with correlations as high as r = 0.87 and lower error estimates compared to both direct LLM predictions and baseline regressors. These findings highlight the promise of LLMs in streamlining item development and reducing reliance on extensive field testing and underscore the importance of structured feature extraction. We provide a seven-step workflow for testing professionals who would want to implement a similar item difficulty estimation approach with their item pool.

ABSTRACT The growing complexity of construction management (CM) projects, coupled with challenges such as strict regulatory requirements and labor shortages, requires specialized analytical tools that streamline project workflow and enhance performance. Although large language models (LLMs) have demonstrated exceptional performance in general reasoning tasks, their effectiveness in tackling CM-specific challenges, such as precise quantitative analysis and regulatory interpretation, remains inadequately explored. To bridge this gap, this study introduces CMExamSet, a comprehensive benchmarking dataset comprising 689 authentic multiple-choice questions sourced from 1 arXiv:2504.08779v1 The results indicate that GPT-4o and Claude 3.7 surpass typical human pass thresholds (70%), with average accuracies of 82% and 83%, respectively. Additionally, both models performed better on single-step tasks, with accuracies of 85.7% (GPT-4o) and 86.7% (Claude 3.7). Multi-step tasks were more challenging, reducing performance to 76.5% and 77.6%, respectively. Our error pattern analysis further reveals that conceptual misunderstandings are the most common (44.4% and 47.9%), underscoring the need for enhanced domain-specific reasoning models. These findings underscore the potential of LLMs as valuable supplementary analytical tools in CM, while highlighting the need for domain-specific refinements and sustained human oversight in complex decision making. INTRODUCTION The construction industry is undergoing a transformation driven by digital technologies, increased project complexity, heterogeneous regulations, and ongoing labor shortages (Abioye et al. 2021). These changes create a pressing need for intelligent tools that can augment human expertise and support decision-making in construction management (CM) (Regona et al. 2022). Among these technologies, large language models (LLMs) such as GPT-4 and Claude have shown a comparative performance in general reasoning, natural language understanding, and educational applications (Ooi et al. 2025).

The rise of deep learning in natural language processing has fostered the creation of text to structured query language models composed of an encoder and a decoder. Researchers have experimented with various intermediate processing like schema linking, table type aware, value extract. To generate accurate SQL results for the user question. However error analysis performed on the failed cases on these systems shows, 29 percentage of the errors would be because the system was unable to understand the values expressed by the user in their question. This challenge affects the generation of accurate SQL queries, especially when dealing with domain-specific terms and specific value conditions, where traditional methods struggle to maintain consistency and precision. To overcome these obstacles, proposed two intermediations like implementing data balancing technique and over sampling domain-specific queries which would refine the model architecture to enhance value recognition and fine tuning the model for domain-specific questions. This proposed solution achieved 10.98 percentage improvement in accuracy of the model performance compared to the state of the art model tested on WikiSQL dataset. to convert the user question accurately to SQL queries. Applying oversampling technique on the domain-specific questions shown a significant improvement as compared with traditional approaches.

Multimodal Retrieval-Augmented Generation (MRAG) enhances large language models (LLMs) by integrating multimodal data (text, images, videos) into retrieval and generation processes, overcoming the limitations of text-only Retrieval-Augmented Generation (RAG). While RAG improves response accuracy by incorporating external textual knowledge, MRAG extends this framework to include multimodal retrieval and generation, leveraging contextual information from diverse data types. This approach reduces hallucinations and enhances question-answering systems by grounding responses in factual, multimodal knowledge. Recent studies show MRAG outperforms traditional RAG, especially in scenarios requiring both visual and textual understanding. This survey reviews MRAG's essential components, datasets, evaluation methods, and limitations, providing insights into its construction and improvement. It also identifies challenges and future research directions, highlighting MRAG's potential to revolutionize multimodal information retrieval and generation. By offering a comprehensive perspective, this work encourages further exploration into this promising paradigm.

ExpertRAG is a novel theoretical framework that integrates Mixture-of-Experts (MoE) architectures with Retrieval Augmented Generation (RAG) to advance the efficiency and accuracy of knowledge-intensive language modeling. We propose a dynamic retrieval gating mechanism coupled with expert routing, enabling the model to selectively consult an external knowledge store or rely on specialized internal experts based on the query's needs. The paper lays out the theoretical foundations of ExpertRAG, including a probabilistic formulation that treats retrieval and expert selection as latent decisions, and mathematical justifications for its efficiency in both computation and knowledge utilization. We derive formulae to quantify the expected computational cost savings from selective retrieval and the capacity gains from sparse expert utilization. A comparative analysis positions ExpertRAG against standard RAG (with always-on retrieval) and pure MoE models (e.g., Switch Transformer, Mixtral) to highlight its unique balance between parametric knowledge and non-parametric retrieval. We also outline an experimental validation strategy, proposing benchmarks and evaluation protocols to test ExpertRAG's performance on factual recall, generalization, and inference efficiency. The proposed framework, although presented theoretically, is supported by insights from prior work in RAG and MoE, and is poised to provide more factual, efficient, and adaptive generation by leveraging the best of both paradigms. In summary, ExpertRAG contributes a new perspective on scaling and augmenting language models, backed by a thorough analysis and a roadmap for empirical validation.

The growing capabilities of large language models (LLMs) present a key challenge of maintaining effective human oversight. Weak-to-strong generalization (W2SG) offers a promising framework for supervising increasingly capable LLMs using weaker ones. Traditional W2SG methods rely on passive learning, where a weak teacher provides noisy demonstrations to train a strong student. This hinders students from employing their knowledge during training and reaching their full potential. In this work, we introduce Alice (pro{A}ctive {l}earning w{i}th tea{c}her's D{e}monstrations), a framework that leverages complementary knowledge between teacher and student to enhance the learning process. We probe the knowledge base of the teacher model by eliciting their uncertainty, and then use these insights together with teachers' responses as demonstrations to guide student models in self-generating improved responses for supervision. In addition, for situations with significant capability gaps between teacher and student models, we introduce cascade Alice, which employs a hierarchical training approach where weak teachers initially supervise intermediate models, who then guide stronger models in sequence. Experimental results demonstrate that our method significantly enhances the W2SG performance, yielding substantial improvements in three key tasks compared to the original W2SG: knowledge-based reasoning (+4.0%), mathematical reasoning (+22.62%), and logical reasoning (+12.11%). This highlights the effectiveness of our new W2SG paradigm that enables more robust knowledge transfer and supervision outcome.