Paolo Torroni

Second cycle degree programmes dissertations

• A Comparison between LLMs and SLMs for Document Processing in the Insurance Sector
• A two-step LLM-augmented distillation method for passage reranking
• Addressing Misinformation Challenges in War Scenario: Russo-Ukrainian War
• An Artificial Intelligence System for the Autonomous Pagination of Newspapers
• An LLM Agent System for Reducing Hallucinations in Drug Discovery Tasks
• An LLM-as-a-judge Comparison of Embedding Models for RAG Tasks in Italian Press News Data
• Argument Mining into Active Learning Systematic Reviews: unlocking the synergy between MARGOT and ASReview
• Automatic Terminology Coding for the Biomedical Domain
• Automating Test Case Generation for Automotive Industry using Large Language Models
• Comprehensive study of clinical entity extraction and classification using Large Language Models
• Continual Learning for Improved Trash Classification in Recycling
• Custom Data Integration for Large Language Models: Investigating Fine-tuning and Retrieval-Augmented Generation
• Design and Implementation of a Neural Machine Translation Engine for Computer-Assisted Translations
• Design and implementation of a privacy-preserving dialogue system based on argumentation
• Developing an Automated ESG Data Extraction and Analysis Tool with NLP Techniques and Large Language Models
• Developing and Comparing Machine Reasoning Models to Humans in NLP Tasks
• Development of an LLM-based system for the generation of multiple-choice English grammar exercises
• Diving into Song Lyrics with Large Language Models: Unveiling Metadata Insights and Fueling Video Lyrics Generation
• Dynamic Few-Shot Learning for Knowledge Graph Question Answering
• Efficient Information Extraction from Logistics Documents using OCR and AI Model: LayoutLMv3
• Efficient Knowledge Distillation for Green NLP Models: Bridging the Gap with Large Language Models
• Empathic Voice: Enabling Emotional Intelligence in Virtual Assistants
• Enhancing Chatbot Efficacy in Italian Language through Retrieval Augmented Generation and LoRA Fine-Tuning
• Enhancing Document Parsing and Question Answering through Optimized Table Parsing
• Enhancing the Software Development Life Cycle with Conversational AI: LLM-Driven Documentation Q&A and Automated Model Evaluation
• Example Sentence Suggestion for Learners of Japanese as a Second Language Using Pretrained Language Models
• Extracting Organization-Location Relations from German News Articles: A Comparative Study of Techniques
• Finetuning commercial Large Language Models with LoRA for enhanced Italian language understanding
• Fine-Tuning Neural Codec Language Models from Feedback with Reinforcement Learning
• From text to knowledge: Large Language Models-based methods for knowledge extraction
• Generation of proprietary code: from the data extraction to the model finetuning and integration in multi agent system
• Generazione e valutazione di test automatici tramite modelli di NLP avanzati
• Graph-Based Keyword Extraction from Scientific Paper Abstracts using Word Embeddings
• Implementing large language model-based machine translation in small and medium-sized enterprises
• Integrating behaviour trees and finite state machines for human-robot interaction
• Leveraging Large Language Models for Content Analysis and Generation for Podcast Transcriptions
• Leveraging Large Language Models for Fact-Checked Claim Retrieval Based On Similarity
• Leveraging LLMs as noisy label generators for named entity recognition
• Machine Learning Approaches for State of Health Estimation of Electric Vehicle Batteries
• Named Entity Recognition for Historical Italian Texts: Overcoming Data Limitations through Strategic Annotation and Model Adaptation
• Neural Clustering on Tree Structured Data: A case study on Argument Mining
• Neural-Symbolic Learning: challenges and benchmarks
• On the use of Prompting for Fine-Tuning Neural models for Speech Processing
• Time Sensitive Networking: implementation of a Real Time communication protocol for Machine to Machine and Controller to Controller communication in a Real Time environment
• Unstructured Knowledge Integration with Annotation Guidelines: A case study on text classification
• Valida: AI and NLP Techniques in Document Forgery Detection
• VerifAi: Towards an Open-Source Scientific Generative Question-Answering System with Referenced and Verifiable Answers
• Zero-Shot Warning Generation for Misinformative Multimodal Content Detection