{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:27:05Z","timestamp":1770917225674,"version":"3.50.1"},"reference-count":35,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T00:00:00Z","timestamp":1697414400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003593","name":"Brazilian fostering agency CNPq (National Council for Scientific and Technological Development)","doi-asserted-by":"publisher","award":["405531\/2022-2"],"award-info":[{"award-number":["405531\/2022-2"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Vehicles"],"abstract":"<jats:p>In the current scenario of fast technological advancement, increasingly characterized by widespread adoption of Artificial Intelligence (AI)-driven tools, the significance of autonomous systems like chatbots has been highlighted. Such systems, which are proficient in addressing queries based on PDF files, hold the potential to revolutionize customer support and post-sales services in the automotive sector, resulting in time and resource optimization. Within this scenario, this work explores the adoption of Large Language Models (LLMs) to create AI-assisted tools for the automotive sector, assuming three distinct methods for comparative analysis. For them, broad assessment criteria are considered in order to encompass response accuracy, cost, and user experience. The achieved results demonstrate that the choice of the most adequate method in this context hinges on the selected criteria, with different practical implications. Therefore, this work provides insights into the effectiveness and applicability of chatbots in the automotive industry, particularly when interfacing with automotive manuals, facilitating the implementation of productive generative AI strategies that meet the demands of the sector.<\/jats:p>","DOI":"10.3390\/vehicles5040076","type":"journal-article","created":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T08:32:57Z","timestamp":1697445177000},"page":"1384-1399","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Analysis of Language-Model-Powered Chatbots for Query Resolution in PDF-Based Automotive Manuals"],"prefix":"10.3390","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6447-3806","authenticated-orcid":false,"given":"Tha\u00eds","family":"Medeiros","sequence":"first","affiliation":[{"name":"UFRN-PPgEEC, Postgraduate Program in Electrical and Computer Engineering, Federal University of Rio Grande do Norte, Natal 59078-970, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7624-5301","authenticated-orcid":false,"given":"Morsinaldo","family":"Medeiros","sequence":"additional","affiliation":[{"name":"UFRN-PPgEEC, Postgraduate Program in Electrical and Computer Engineering, Federal University of Rio Grande do Norte, Natal 59078-970, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4609-8800","authenticated-orcid":false,"given":"Mariana","family":"Azevedo","sequence":"additional","affiliation":[{"name":"UFRN-PPgEEC, Postgraduate Program in Electrical and Computer Engineering, Federal University of Rio Grande do Norte, Natal 59078-970, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8277-7571","authenticated-orcid":false,"given":"Marianne","family":"Silva","sequence":"additional","affiliation":[{"name":"UFRN-PPgEEC, Postgraduate Program in Electrical and Computer Engineering, Federal University of Rio Grande do Norte, Natal 59078-970, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0116-6489","authenticated-orcid":false,"given":"Ivanovitch","family":"Silva","sequence":"additional","affiliation":[{"name":"UFRN-PPgEEC, Postgraduate Program in Electrical and Computer Engineering, Federal University of Rio Grande do Norte, Natal 59078-970, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3988-8476","authenticated-orcid":false,"given":"Daniel G.","family":"Costa","sequence":"additional","affiliation":[{"name":"INEGI, Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2023,10,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1353\/hpn.2023.a899427","article-title":"Potentialities of Applied Translation for Language Learning in the Era of Artificial Intelligence","volume":"106","author":"Neville","year":"2023","journal-title":"Hispania"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Shinde, P.P., and Shah, S. (2018, January 16\u201318). A review of machine learning and deep learning applications. Proceedings of the 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), Pune, India.","DOI":"10.1109\/ICCUBEA.2018.8697857"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1007\/s10869-022-09864-6","article-title":"A paradigm shift from \u201chuman writing\u201d to \u201cmachine generation\u201d in personality test development: An application of state-of-the-art natural language processing","volume":"38","author":"Lee","year":"2023","journal-title":"J. Bus. Psychol."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ghosh, R.K., Banerjee, A., Aich, P., Basu, D., and Ghosh, U. (2022). Intelligent Internet of Things for Healthcare and Industry, Springer.","DOI":"10.1007\/978-3-030-81473-1"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"040016","DOI":"10.1063\/5.0125264","article-title":"Development of a chatbot for a car service","volume":"Volume 2700","author":"Rubleva","year":"2023","journal-title":"Proceedings of the AIP Conference Proceedings"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2034","DOI":"10.1109\/TIV.2023.3252571","article-title":"Chat with ChatGPT on interactive engines for intelligent driving","volume":"8","author":"Gao","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"81","DOI":"10.54097\/fcis.v2i2.4465","article-title":"The benefits and challenges of ChatGPT: An overview","volume":"2","author":"Deng","year":"2022","journal-title":"Front. Comput. Intell. Syst."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.iotcps.2023.04.003","article-title":"ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope","volume":"3","author":"Ray","year":"2023","journal-title":"Internet Things-Cyber-Phys. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Abdullah, M., Madain, A., and Jararweh, Y. (December, January 28). ChatGPT: Fundamentals, applications and social impacts. Proceedings of the 2022 Ninth International Conference on Social Networks Analysis, Management and Security (SNAMS), Milan, Italy.","DOI":"10.1109\/SNAMS58071.2022.10062688"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/j.iotcps.2023.05.004","article-title":"ChatGPT: Vision and challenges","volume":"3","author":"Gill","year":"2023","journal-title":"Internet Things-Cyber-Phys. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"20220041","DOI":"10.1098\/rsta.2022.0041","article-title":"Symbols and grounding in large language models","volume":"381","author":"Pavlick","year":"2023","journal-title":"Philos. Trans. R. Soc. A"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Boukhers, Z., and Bouabdallah, A. (2022, January 20\u201324). Vision and natural language for metadata extraction from scientific PDF documents: A multimodal approach. Proceedings of the 22nd ACM\/IEEE Joint Conference on Digital Libraries, Cologne, Germany.","DOI":"10.1145\/3529372.3533295"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1186\/s13643-023-02243-z","article-title":"Are ChatGPT and large language models \u201cthe answer\u201d to bringing us closer to systematic review automation?","volume":"12","author":"Qureshi","year":"2023","journal-title":"Syst. Rev."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Diniz da Silva, M.B., Vieira, E., Silva, I., Silva, D., Ferrari, P., Rinaldi, S., and Carvalho, D.F. (2018, January 25\u201328). A customer feedback platform for vehicle manufacturing in Industry 4.0. Proceedings of the 2018 IEEE Symposium on Computers and Communications (ISCC), Natal, Brazil.","DOI":"10.1109\/ISCC.2018.8538554"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Silva, M., Flores, T., Andrade, P., Silva, J., Silva, I., and Costa, D.G. (2022, January 17\u201320). An Online Unsupervised Machine Learning Approach to Detect Driving Related Events. Proceedings of the IECON 2022\u201448th Annual Conference of the IEEE Industrial Electronics Society, Brussels, Belgium.","DOI":"10.1109\/IECON49645.2022.9968381"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1579","DOI":"10.1177\/03611981221125744","article-title":"SmarTxT: A Natural Language Processing Approach for Efficient Vehicle Defect Investigation","volume":"2677","author":"Francis","year":"2023","journal-title":"Transp. Res. Rec."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2020","DOI":"10.1109\/TIV.2023.3253281","article-title":"Chat with chatgpt on intelligent vehicles: An ieee tiv perspective","volume":"8","author":"Du","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2236","DOI":"10.11591\/eei.v12i4.4990","article-title":"License plate recognition in slow motion vehicles","volume":"12","author":"Aljelawy","year":"2023","journal-title":"Bull. Electr. Eng. Inform."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"120127","DOI":"10.1016\/j.eswa.2023.120127","article-title":"Word and character segmentation in ancient handwritten documents in Devanagari and Maithili scripts using horizontal zoning","volume":"225","author":"Jindal","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2145639","DOI":"10.1080\/08839514.2022.2145639","article-title":"HR-Specific NLP for the Homogeneous Classification of Declared and Inferred Skills","volume":"36","author":"Celsi","year":"2022","journal-title":"Appl. Artif. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"100856","DOI":"10.1016\/j.rineng.2022.100856","article-title":"A comparison of chatbot platforms with the state-of-the-art sentence BERT for answering online student FAQs","volume":"17","author":"Peyton","year":"2023","journal-title":"Results Eng."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1007\/978-981-33-4305-4_30","article-title":"A Contextual Model for Information Extraction in Resume Analytics Using NLP\u2019s Spacy","volume":"Volume 173 LNNS","author":"Channabasamma","year":"2021","journal-title":"Inventive Computation and Information Technologies"},{"key":"ref_23","unstructured":"Huang, Y. (2023, August 23). How To Create A Doc ChatBot That Learns Everything For You, In 15 Minutes. Available online: https:\/\/levelup.gitconnected.com\/how-to-create-a-doc-chatbot-that-learns-everything-for-you-in-15-minutes-364fef481307."},{"key":"ref_24","unstructured":"Liu, J. (2023, August 23). LlamaIndex. Available online: https:\/\/github.com\/jerryjliu\/llama_index."},{"key":"ref_25","unstructured":"Documentation, L. (2023, August 23). Introduction. Available online: https:\/\/python.langchain.com\/docs\/get_started\/introduction.html."},{"key":"ref_26","unstructured":"API, O. (2023, August 23). OpenAI API. Available online: https:\/\/openai.com\/blog\/openai-api."},{"key":"ref_27","unstructured":"AO, A. (2023, August 23). Langchain Ask PDF (Tutorial). Available online: https:\/\/github.com\/alejandro-ao\/langchain-ask-pdf."},{"key":"ref_28","unstructured":"Documentation, S. (2023, August 23). Streamlit Documentation. Available online: https:\/\/docs.streamlit.io\/."},{"key":"ref_29","unstructured":"Allahyari, M. (2023, August 23). Leveraging LangChain and Large Language Models for Accurate PDF-Based Question Answering. Available online: https:\/\/github.com\/mallahyari\/drqa."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Reimers, N., and Gurevych, I. (2019, January 3\u20137). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, Hong Kong, China.","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref_31","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., and Askell, A. (2020). Language Models are Few-Shot Learners. arXiv."},{"key":"ref_32","unstructured":"Pricing, O. (2023, August 23). OpenAI Pricing. Available online: https:\/\/openai.com\/pricing."},{"key":"ref_33","unstructured":"Documentation, H.F. (2023, August 23). All-Mpnet-Base-v2. Available online: https:\/\/huggingface.co\/sentence-transformers\/all-mpnet-base-v2."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Jim\u00e9nez, S., Favela, J., Quezada, \u00c1., Alanis, A., Castillo, E., and Villegas, E. (2022, January 12\u201314). Alexa to support patients with dementia and family caregivers in challenging behaviors. Proceedings of the World Conference on Information Systems and Technologies, Online.","DOI":"10.1007\/978-3-031-04826-5_33"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2557","DOI":"10.1080\/10447318.2022.2080899","article-title":"Factors affecting innovation resistance of smartphone AI Voice Assistants","volume":"39","author":"Hong","year":"2023","journal-title":"Int. J. Hum. Comput. Interact."}],"container-title":["Vehicles"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2624-8921\/5\/4\/76\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:07:36Z","timestamp":1760130456000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2624-8921\/5\/4\/76"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,16]]},"references-count":35,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["vehicles5040076"],"URL":"https:\/\/doi.org\/10.3390\/vehicles5040076","relation":{},"ISSN":["2624-8921"],"issn-type":[{"value":"2624-8921","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,16]]}}}