From User Preferences to Optimization Constraints Using Large Language Models
This work addresses the challenge of integrating user preferences into energy optimization systems for renewable energy communities, but it is incremental as it focuses on baseline evaluation and dataset creation without introducing new methods.
The paper tackles the problem of translating natural language user preferences into formal optimization constraints for home appliances in renewable energy communities, specifically in the Italian scenario, by evaluating various LLMs and establishing baseline performance with a publicly released dataset.
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