Argomenti di tesi proposti dal docente.
Ultime tesi seguite dal docente
Tesi di Laurea
- Integrazione di Agenti Conversazionali e Large Language
Models per la Gestione Automatizzata dei Ticket di
Help Desk Aziendali
- A Systematic Review on Automatic Prompt Learning
- Benchmarking e Adapter Fine-tuning di Large Language Model nella Risoluzione di Quesiti sul Programma di Sviluppo Rurale Italiano
- Controllable Question Answering through Learned Representations: A Sparse Autoencoder Approach to LLM Steering
- Creazione di una pipeline di acquisizione continua di report sec Edgar per analisi finanziarie basate su machine learning
- Development of a Retrieval-Enhanced Chatbot for the Italian Workplace Safety Regulation in Low-Resource Settings
- Evaluating Visual Grounding in Multimodal Large Language Models for Medical Question Answering
- GRPO4Chess: Improving Next Move Generation in Chess Language Models via Reinforcement Learning
- Guidare i Large Language Models nell'Estrazione di Informazioni da Database mediante Query SQL Automatizzate e Model Context Protocol
- Interpretare i Soft Prompts: Analisi delle Tecniche di
Parameter-Efficient Fine-Tuning per il Biomedical NER
- Language Models for ICD Coding: Benchmarking Generative and Retrieval Approaches on Multimodal Clinical Data
- Large Language Models for Interpretive Question Answering over Cross-Referenced Legal Documents in Evolving Knowledge Bases
- Latent-GEPA: Accelerating Prompt Optimization via Embedding Inversion and Latent Semantic Guidance in Large Language Models
- Migliorare le Prestazioni dei Large Language Models nella Traduzione delle Lingue Sottorappresentate mediante Knowledge Graph e Wordnet
- Modelli predittivi per il rischio di default e l'analisi settoriale su dati finanziari dell'euro zona
- Multimodal Generative Information Retrieval of Chest X-Rays Grounded on ICD-9 Taxonomy
- Obduracy: Fine-Tuning at What Cost? Evaluating Specialization Rigidity, Catastrophic Forgetting and Decoding Variability in Large Language Models
- On-Device Retrieval-Augmented Generation over Personal Clinical Records
- OpenBioNER-MoE: Mixture of Domain-Specific Encoders for Zero-Shot Biomedical Named Entity Recognition
- OrienterAI: An Efficient Hybrid RAG Chatbot for Orienting Citizens Toward the Emilia-Romagna Educational Offer
- Overcoming Long-Context Limitations in Large Language Models through Retrievable and Composable Doc-to-LoRA Parametric Memories
- Ragionamento visivo nei large language
model multimodali per la risoluzione di
puzzle scacchistici
- Studio Comparativo di Modelli Avanzati per la Predizione del Rendimento di Titoli Azionari
- Teaching an Auditor to Look Away: A Fine-Tuning Backdoor for Selective Vulnerability Blindness in Code LLMs
Tesi di Laurea Magistrale
- Automated Classification of Multilingual User Feedback in Fitness Applications Through Hybrid Retrieval and Large Language Models
- Automatic Optimization of Agentic Pipelines for Protein Function Prediction
- Chess-Reachy: Autonomous Robotic Chess Gameplay through Large Language Models and Model Context Protocol
- Enhancing Entity Representations through Soft Prompt Tuning: An Efficient Approach to Biomedical Named Entity Recognition
- Foundational Transformer Models for Financial Time Series Forecasting
- Graph-of-Mark: Graph-Based Visual Prompting for Enhanced Spatial Reasoning in Multimodal Language Models
- Guiding the Chain of Thought of Mixture-of-Experts LLMs via Routing Intervention for Efficient Reasoning
- ICD Coding as Generative Retrieval: Taxonomy-Grounded Autoregressive Code Generation from Clinical Text and Chest Radiographs
- Multimodal Retrieval-Enhanced Large Language Models for Pictogram Interaction in Augmentative and Alternative Communication
- RadRelBench: A Benchmark for Deep Learning on Multimodal Relational Databases of Chest Radiographs
- Retrieval and Transition Modeling for Next-Occupation Prediction
- State-Grounded GUI Agents for Long-Horizon Tasks in Web Environments
- Unsupervised Optimization of Accuracy and Interpretability in Multimodal Models for Medical Disease Diagnosis
Tesi di Dottorato
- Optimization in large language models: innovative approaches leveraging knowledge distillation and pruning
