The ALICE (A Large Ion Collider Experiment) detector at the Large Hadron Collider (LHC), operated by the European Organization for Nuclear Research (CERN), is dedicated to heavy-ion collisions. Within ALICE, the application logs of the online computing systems are consolidated through a logging system known as Infologger, which integrates data from various sources. To identify potential anomalies, shifters in the control room manually review logs for anomalies, which require significant expertise and pose challenges due to the frequent onboarding of new personnel. To address this issue, we propose a real-time semi-supervised log anomaly detection framework designed to automatically detect anomalies in ALICE operations. The framework leverages BERTopic, a topic modeling technique, to provide real-time insights for incoming log messages for shifters. This includes an analytical dashboard that represents the anomaly status in log messages, facilitating informative monitoring for shifters. Through evaluation, including Infologger and BGL (BlueGene/L supercomputer), we analyze the effects of word embeddings, clustering algorithms, and HDBSCAN hyperparameters on model performance. The result demonstrates that the BERTopic can enhance the log anomaly detection process over traditional topic models, achieving remarkable performance metrics and attaining F1-scores of 0.957 and 0.958 for the InfoLogger and BGL datasets, respectively, even without the preprocessing technique.
Artificial intelligence (AI) is rapidly transforming education, presenting unprecedented opportunities for personalized learning and streamlined content creation. However, realizing the full potential of AI in educational settings necessitates careful consideration of the quality, cognitive depth, and ethical implications of AI-generated materials. This paper synthesizes insights from four related studies to propose a comprehensive framework for enhancing AI-driven educational tools. We integrate cognitive assessment frameworks (Bloom's Taxonomy and SOLO Taxonomy), linguistic analysis of AI-generated feedback, and ethical design principles to guide the development of effective and responsible AI tools. We outline a structured three-phase approach encompassing cognitive alignment, linguistic feedback integration, and ethical safeguards. The practical application of this framework is demonstrated through its integration into OneClickQuiz, an AI-powered Moodle plugin for quiz generation. This work contributes a comprehensive and actionable guide for educators, researchers, and developers aiming to harness AI's potential while upholding pedagogical and ethical standards in educational content generation.
High-precision knowledge retrieval within specialized scientific infrastructures, such as CERN's large-scale data ecosystem, presents unique challenges for standard Large Language Models (LLMs). Conventional Retrieval-Augmented Generation (RAG) frameworks often suffer from structural fragmentation and inadequate retrieval of technical identifiers. This paper proposes an optimized RAG framework utilizing a Hybrid Similarity Scoring mechanism that integrates BM25 lexical matching with dense semantic retrieval. The methodology focuses on enhancing technical factuality through a neural re-ranking pipeline and instruction-formatted system prompting. Extensive experiments were conducted to evaluate three distinct chunking strategies and the influence of various LLM hyperparameters on model grounding. Results indicate that the proposed framework achieves a 2–8% improvement in retrieval relevance and a 2% reduction in hallucinations compared to standard RAG baselines, providing a robust solution for complex technical domain interaction.