ChatGPT in the Generation of Explanations for Cyber-Physical Systems

Peña-Cáceres O.; Silva-Marchan H.; Espinoza-Nima R.; Garay-Silupu E.; Ricalde-Morán D.; Alvarado-Paiva D. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2024) · DOI: 10.18687/laccei2024.1.1.1588

Resumen

The research focused on designing a mechanism for the generation of explanations in the smart home environment through ChatGPT with the purpose of dynamizing the interaction between humans and cyber-physical systems. A simulator was developed that integrates different services and explanation objects related to the smart home environment. The simulator interacts with an artificial intelligence model to determine the level of attention required by the user, the type of explanation, and the interaction mechanism. The ChatGPT text-davinci-003 model was used to generate explanations. For the evaluation, a checklist was applied to 20 professionals linked to the study area in order to determine the quality of the system and the effectiveness of ChatGPT in the generation of explanations for cyber-physical systems in the context of the smart home. The system provided favorable results, with outstanding scores on the quality of explanations (95%), user-system interaction (90%), and adaptability and robustness (95%). The explanations varied between 15 and 50 words, depending on the scenario. Each explanation generated by the system has proven to be clear and understood by users. The explanations that focus on answering the “What” of a scenario are brief and the “Why” explanations are longer. For future research, it is recommended to explore the GPT-3.5-turbo-instructions and Davinci-002 models, as well as to consider the inclusion of new forms of explanation, referring to “why not” and “how” the user should execute the tasks that the system has inferred.

Instituciones: Universidad Nacional de Piura; Universidad Nacional de Tumbes; Universidad César Vallejo