Knowledge engineering for semantic understanding

This thesis addresses the challenges of improving semantic understanding in conversational agents by combining Knowledge Graphs (KGs) and Large Language Models (LLMs) within a flexible, multi-domain knowledge plugin architecture. We explore the inherent difficulties LLMs face in interpreting plain-text user queries, as well as the limitations of generative AI, particularly its tendency toward “hallucination” when generating responses. To mitigate this, we examine the complex process of extracting and structuring knowledge from raw text to construct KGs that serve as authoritative, context-rich foundations for information retrieval. The knowledge plugin architecture developed in this work enables conversational agents to leverage both KGs and LLMs to interact accurately with reliable, domain-specific sources. Our approach includes techniques such as fine-tuning and intelligent fewshot prompting to enhance LLMs’ ability to generate accurate, context-aware queries and responses over KGs. This integration significantly advances the potential for scalable, adaptable conversational agents capable of reliable information retrieval across multiple domains. The insights and techniques outlined in this thesis mark a critical step toward creating domain-agnostic AI systems that deliver semantically precise and trustworthy information.

Grantor dc:publisher

Università degli Studi di Cagliari

Year dc:date

2025

Author dc:creator

• MELONI, ANTONELLO

Contributors dc:contributor

• REFORGIATO RECUPERO, DIEGO ANGELO GAETANO
• IANNIZZOTTO, ANTONIO

• Scholarly Data
• Knowledge Graph
• Virtual Assistant
• User Experience
• Human-Robot Interaction
• Information Extraction
• Natural Language Processing
• Course Recommendation
• Conversational Agents, Labor Market, Large Language Models, Natural Language Processing, Occupational Database
• Question answering
• Fine-tuning
• Few-shot learning
• Abstract Meaning Representation
• Semantic Frames
• Settore INF/01 - Informatica
• Settore INFO-01/A - Informatica

Language dc:language

eng

Handle dc:identifier

https://hdl.handle.net/11584/442245

OAI identifier oai:identifier

oai:iris.unica.it:11584/442245