KEYWORD |
DAUIN - GR-10 - Intelligent and Interactive Systems - e-LITE
Leveraging Large Language Models for Interaction with Smart Environments
keywords ARTIFICIAL INTELLIGENCE, HUMAN-COMPUTER INTERACTION, LARGE-SCALE LANGUAGE MODELS, MACHINE LEARNING, NATURAL LANGUAGE PROCESSING, SMART HOME
Reference persons LUIGI DE RUSSIS
External reference persons Tommaso Calò
Research Groups DAUIN - GR-10 - Intelligent and Interactive Systems - e-LITE
Thesis type EXPERIMENTAL, RESEARCH
Description This thesis addresses the challenge of enhancing user interaction with smart environments through the application of large language models. Over the past decade, there has been significant progress in the field of natural language processing (NLP), especially with the advent of transformer-based models such as GPT-3 and GPT-4. These models have displayed remarkable capabilities in understanding and generating human-like text, opening up possibilities for numerous applications, including improving end-user interaction in smart environments, e.g., smart homes.
This thesis aims to explore how large language models can be leveraged to make these interactions more natural and intuitive, using natural language as the primary mode of communication.
The main goals of the thesis are:
* Review and understand the current state of the art in large language models and smart environments.
* Design and implement a system that uses a large language model to facilitate user interaction with a smart environment.
* Conduct experiments to evaluate the effectiveness of the designed system.
See also leveraging large language models for end user interaction with smart environments.pdf
Required skills Good programming skills and Python knowledge are required.
Deadline 18/07/2023
PROPONI LA TUA CANDIDATURA