This work explores using Large Language Models (LLMs) to translate user preferences into energy optimization constraints for home appliances. We describe a task where natural language user utterances are converted into formal constraints for smart appliances, within the broader context of a renewable energy community (REC) and in the Italian scenario. We evaluate the effectiveness of various LLMs currently available for Italian in translating these preferences resorting to classical zero-shot, one-shot, and few-shot learning settings, using a pilot dataset of Italian user requests paired with corresponding formal constraint representation. Our contributions include establishing a baseline performance for this task, publicly releasing the dataset and code for further research, and providing insights on observed best practices and limitations of LLMs in this particular domain
@article{arxiv.2503.21360,
title = {From User Preferences to Optimization Constraints Using Large Language Models},
author = {Manuela Sanguinetti and Alessandra Perniciano and Luca Zedda and Andrea Loddo and Cecilia Di Ruberto and Maurizio Atzori},
journal= {arXiv preprint arXiv:2503.21360},
year = {2025}
}