Using the Large Language Model ChatGPT to Support Decisions in Sustainable Transport

Paweł Ziemba () and Filip Majewski
Additional contact information
Paweł Ziemba: Institute of Management, University of Szczecin, 70-453 Szczecin, Poland
Filip Majewski: Faculty of Computer Science and Telecommunications, Maritime University of Szczecin, 70-500 Szczecin, Poland

Sustainability, 2025, vol. 17, issue 16, 1-22

Abstract: Recently, the popularity of large language models (LLMs) used as artificial intelligence tools supporting humans has been growing. LLMs are applied in many fields, including increasingly for various sustainability-related issues. One of the most popular tools of this type is ChatGPT, which, after being supplied with appropriate knowledge, can act as a domain expert, including in the area of sustainable transport. The article uses this functionality of ChatGPT, feeding it with knowledge about electric vehicles (EVs) available on the Polish market. The aim of the research was to develop a solution based on an LLM, which will act as an advisor when buying an EV. After appropriate modelling of knowledge and feeding it into ChatGPT, an expert system was obtained, which, based on the defined needs of the user, recommends the most suitable EV for them. When answering the system’s questions, the user provides only a description of the decision-making situation at the LLM input (e.g., the locations to which they are travelling, information on the number of family members, etc.). In turn, the appropriately fine-tuned ChatGPT provides a recommendation of vehicles that meet the user’s defined needs. This is a very user-friendly solution because it does not require the user to precisely define the vehicle evaluation criteria or a set of alternatives. This approach also does not require the user to have detailed domain knowledge.

Keywords: sustainable transport; electric vehicles; sustainability; expert system; sustainable decisions; ChatGPT; large language model; fine-tuning (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/17/16/7520/pdf (application/pdf)
https://www.mdpi.com/2071-1050/17/16/7520/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:17:y:2025:i:16:p:7520-:d:1728554

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().