large language models

Data Quality, Feature Engineering, and Model Reliability in Large-Scale AI Multi-Agentic Systems

Large-scale artificial intelligence (AI) systems increasingly operate not as a single monolithic model but as a population of interacting, specialized agents separate models or decision-making components responsible for functions such as pricing, fraud detection, ranking, routing, and customer support that share underl...

Scalable Real-Time Data Pipelines for AI and Machine Learning–Driven Enterprise Systems

The growth of enterprise data volumes across the 2000s and 2010s pushed traditional batch-oriented data processing infrastructures past their practical limits, motivating a sustained shift toward distributed, stream-based architectures capable of supporting real-time analytics and machine learning (ML). This article sy...

Ferran32/Master-Thesis-Code: v1.0 – Thesis version (MSc thesis, KTH, 2026)

Code, data and analysis outputs accompanying the MSc thesis "An Empirical Comparison of Prompting, Label-Only Fine-Tuning, and Skill Refinement for Software Vulnerability Detection with Large Language Models" (Ferran Solanes Serrat, KTH Royal Institute of Technology, 2026). Code: MIT licence. The MVFSC benchmark in dat...

An AI-interpretable multidimensional intelligence-driven framework for student performance prediction using local LLM-based narrative reasoning

Predicting student performance has become a vital objective in educational data mining, however existing models remain limited by limited feature sets, opaque decision processes, and the absence of real-time, context-aware interpretative intelligence. This study presents a novel hybrid Artificial Intelligence (AI) arch...

Comparing Genetic Algorithms and LLMs for Research-Hypothesis Generation: Mainstream Convergence of LLMs, Wider Hypothesis Exploration by Combinatorial Search, and the Limits of Literature-Distance Novelty Metrics

Large language model (LLM)-based creative AI systems tend to produce plausible rather than novel research ideas. This study compares two ways of generating research hypotheses: a genetic algorithm (GA) that recombines Method, Problem, and Goal elements under a fitness function rewarding distance from the literature and...

Functional Verification Using Large Language Models

The Modern Approaches for Representation of Semantic Information in AI Systems and Large Language Models

Cross-Domain Fake News Classification via RoBERTa Fine-Tuning on Hybrid LIAR-FakeNewsNet Corpus with Deployable Web Inference

The rapid spread of misinformation on social media platforms escalates a serious threat to world socio-political stability, health and financial security. While current automated fake news detection models boast impressive accuracy scores, these are often due to memorisation of the training domain rather than genuine g...

Dataset and experimental materials for evaluating LLM reliability in transport planning

This dataset contains the experimental materials for a study on whether publicly accessible conversational large language models (ChatGPT, Claude, Gemini and Microsoft Copilot) can generate road freight driver schedules that comply with EU driving-time and rest-period rules (Regulation (EC) No 561/2006 and Regulation (...

From Human Speakers to Algorithmic Interfaces: Rethinking Ethos in AI-Mediated Communication

Generative Artificial Intelligence (GAI) systems increasingly function as communicative agents, raising questions about how credibility is constructed in them. Drawing on Aristotle's concept of ethos, this study examines how credibility is performed through interface‑level cues in large language model (LLM) chatbots: C...

Blind Letterform Construction as a Behavioral Marker of Geometric Consistency in Large Language Models

A Large-Scale Multi-Domain Unified Reverse Arabic Dictionary Dataset

Abstract Arabic is a linguistically and culturally rich language with a vast vocabulary that spans scientific, religious, and literary domains. However, large-scale lexical datasets linking Arabic words to precise definitions remain limited. We present MURAD (Multi-domain Unified Reverse Arabic Dictionary), an open lex...