Reading comprehension tests are a common way of assessing a language learner's ability. The difficulty of a reading comprehension test is often determined by the balance of factoid and inferential questions. While factoid questions test retrieval of explicitly…
Mixture-of-Experts (MoE) architectures decouple representational capacity from per-token computational cost: each input activates only a few specialised experts, yielding far greater capacity than dense models at equal activation cost. Federated Learning (FL)…
This thesis evaluates the performance and adversarial robustness of four transformer-based language models; BERT, RoBERTa, DistilBERT, and GPT-2 which were fine-tuned for binary phishing email classification. Two preprocessing configurations (Basic and Advance…
Background Transformer-based language models dominate modern natural language processing but impose substantial computational costs during full fine-tuning, limiting accessibility on consumer-grade hardware. Knowledge Distillation and Low-Rank Adaptation (LoRA…
This thesis investigates two complementary axes for improving Large Language Models (LLMs): the architecture used during pretraining, and the reasoning behavior elicited during post-training. The first part of the thesis addresses well-documented optimization…
Scholarship evaluation is a labor-intensive process in which human reviewers are required to assess a large amount of applicant documents. This study presents the design,implementation, and empirical evaluation of a scholarship system that integrates large lan…
Large language models (LLMs) have reshaped natural language processing, demonstrating remarkable reasoning across diverse tasks. Their rapid real-world integration has fostered growing reliance on their perceived cognitive abilities, with users expecting model…
Large language models (LLMs) have become a common sight in day-to-day activities and have found use for a wide range of tasks, many of them of a creative nature. While not perfect, these models have enabled automation of tasks that were previously difficult to…
In recent years, we have witnessed an impressive rise in the ubiquity of large language models (LLMs). Although their fundamental objective, predicting the most probable next word in a sequence, has remained unchanged, the models themselves have expanded drama…
Startups are drivers of innovation and economic growth, but the uncertainty associated with startups makes the evaluation of their innovativeness difficult. Currently, startups are mostly evaluated by experts (e.g., domain experts, potential investors, researc…
Automatic text simplification (ATS) is crucial for accessibility, yet it remains underexplored for low-resource languages. This thesis investigates sentence-level ATS for Catalan using large language models (LLMs). A performance analysis of three LLMs is condu…
Large language models (LLMs) are increasingly deployed in high-stakes settings such as finance, healthcare, and education, where failures in safety and fairness can cause real harm. In this dissertation, we advance LLM trustworthiness by (i) benchmarking how L…
أنا مساعد المستودع. اسألني عن الرسائل والأطاريح حسب الموضوع أو الجامعة أو الدولة أو السنة أو الدرجة، أو اطلب أعداداً وإحصاءات.
يجيب من قاعدة بيانات المستودع فقط، ولا يخترع سجلات أو أرقاماً. لا يُحفظ ما تكتبه على الخادم.
قد يخطئ المساعد أحياناً، فراجع المصادر المرفقة.
