{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:50:41Z","timestamp":1777423841108,"version":"3.51.4"},"reference-count":24,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2024,9,14]],"date-time":"2024-09-14T00:00:00Z","timestamp":1726272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Harnessing the power of Large Language Models (LLMs), this study explores the use of three state-of-the-art LLMs, specifically GPT-3.5-turbo, LLaMA3-8B, and LLaMA3-70B, for crash severity analysis and inference, framing it as a classification task. We generate textual narratives from original traffic crash tabular data using a pre-built template infused with domain knowledge. Additionally, we incorporated Chain-of-Thought (CoT) reasoning to guide the LLMs in analyzing the crash causes and then inferring the severity. This study also examine the impact of prompt engineering specifically designed for crash severity inference. The LLMs were tasked with crash severity inference to: (1) evaluate the models\u2019 capabilities in crash severity analysis, (2) assess the effectiveness of CoT and domain-informed prompt engineering, and (3) examine the reasoning abilities with the CoT framework. Our results showed that LLaMA3-70B consistently outperformed the other models, particularly in zero-shot settings. The CoT and Prompt Engineering techniques significantly enhanced performance, improving logical reasoning and addressing alignment issues. Notably, the CoT offers valuable insights into LLMs\u2019 reasoning process, unleashing their capacity to consider diverse factors such as environmental conditions, driver behavior, and vehicle characteristics in severity analysis and inference.<\/jats:p>","DOI":"10.3390\/computers13090232","type":"journal-article","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T07:36:00Z","timestamp":1726472160000},"page":"232","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Leveraging Large Language Models with Chain-of-Thought and Prompt Engineering for Traffic Crash Severity Analysis and Inference"],"prefix":"10.3390","volume":"13","author":[{"given":"Hao","family":"Zhen","sequence":"first","affiliation":[{"name":"School of Environmental, Civil, Agricultural, and Mechanical Engineering, University of Georgia, Athens, GA 30605, USA"}]},{"given":"Yucheng","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computing, University of Georgia, Athens, GA 30605, USA"}]},{"given":"Yongcan","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Environmental, Civil, Agricultural, and Mechanical Engineering, University of Georgia, Athens, GA 30605, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4823-6322","authenticated-orcid":false,"given":"Jidong J.","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Environmental, Civil, Agricultural, and Mechanical Engineering, University of Georgia, Athens, GA 30605, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9170-2424","authenticated-orcid":false,"given":"Ninghao","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computing, University of Georgia, Athens, GA 30605, USA"}]}],"member":"1968","published-online":{"date-parts":[[2024,9,14]]},"reference":[{"key":"ref_1","first-page":"100113","article-title":"Big data, traditional data and the tradeoffs between prediction and causality in highway-safety analysis","volume":"25","author":"Mannering","year":"2020","journal-title":"Anal. Methods Accid. Res."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1061\/(ASCE)0733-947X(2003)129:4(342)","article-title":"Relationships among urban freeway accidents, traffic flow, weather, and lighting conditions","volume":"129","author":"Golob","year":"2003","journal-title":"J. Transp. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.1016\/j.aap.2007.02.001","article-title":"A joint econometric analysis of seat belt use and crash-related injury severity","volume":"39","author":"Eluru","year":"2007","journal-title":"Accid. Anal. Prev."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/j.tra.2010.02.001","article-title":"The statistical analysis of crash-frequency data: A review and assessment of methodological alternatives","volume":"44","author":"Lord","year":"2010","journal-title":"Transp. Res. Part Policy Pract."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1666","DOI":"10.1016\/j.aap.2011.03.025","article-title":"The statistical analysis of highway crash-injury severities: A review and assessment of methodological alternatives","volume":"43","author":"Savolainen","year":"2011","journal-title":"Accid. Anal. Prev."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/S0001-4575(01)00033-1","article-title":"Effects of road geometry and traffic volumes on rural roadway accident rates","volume":"34","author":"Karlaftis","year":"2002","journal-title":"Accid. Anal. Prev."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"106811","DOI":"10.1016\/j.aap.2022.106811","article-title":"Inferring heterogeneous treatment effects of work zones on crashes","volume":"177","author":"Zhang","year":"2022","journal-title":"Accid. Anal. Prev."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"106835","DOI":"10.1016\/j.aap.2022.106835","article-title":"Exploring factors affecting the injury severity of freeway tunnel crashes: A random parameters approach with heterogeneity in means and variances","volume":"178","author":"Pervez","year":"2022","journal-title":"Accid. Anal. Prev."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.aap.2017.08.026","article-title":"Construction accident narrative classification: An evaluation of text mining techniques","volume":"108","author":"Goh","year":"2017","journal-title":"Accid. Anal. Prev."},{"key":"ref_10","first-page":"1338","article-title":"Identifying secondary crashes using text mining techniques","volume":"12","author":"Zhang","year":"2020","journal-title":"J. Transp. Saf. Secur."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1016\/j.iatssr.2021.01.001","article-title":"Applying interpretable machine learning to classify tree and utility pole related crash injury types","volume":"45","author":"Das","year":"2021","journal-title":"IATSS Res."},{"key":"ref_12","unstructured":"OpenAI (2024, June 14). GPT-3.5 Turbo Updates. Available online: https:\/\/platform.openai.com\/docs\/models\/gpt-3-5-turbo."},{"key":"ref_13","unstructured":"AI@Meta (2024, June 14). Llama 3 Model Card. Available online: https:\/\/www.meta.ai."},{"key":"ref_14","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Wu, X., Yao, W., Chen, J., Pan, X., Wang, X., Liu, N., and Yu, D. (2023). From language modeling to instruction following: Understanding the behavior shift in llms after instruction tuning. arXiv.","DOI":"10.18653\/v1\/2024.naacl-long.130"},{"key":"ref_16","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref_17","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_18","unstructured":"Yin, W. (2020). Meta-learning for few-shot natural language processing: A survey. arXiv."},{"key":"ref_19","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Qin, C., Zhang, A., Zhang, Z., Chen, J., Yasunaga, M., and Yang, D. (2023, January 6\u201310). Is ChatGPT a General-Purpose Natural Language Processing Task Solver?. Proceedings of the The 2023 Conference on Empirical Methods in Natural Language Processing, Singapore.","DOI":"10.18653\/v1\/2023.emnlp-main.85"},{"key":"ref_21","unstructured":"Zhang, Z., Zhang, A., Li, M., Zhao, H., Karypis, G., and Smola, A. (2023). Multimodal Chain-of-Thought reasoning in language models. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Lyu, Q., Havaldar, S., Stein, A., Zhang, L., Rao, D., Wong, E., Apidianaki, M., and Callison-Burch, C. (2023, January 1\u20134). Faithful Chain-of-Thought Reasoning. Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL 2023), Bali, Indonesia.","DOI":"10.18653\/v1\/2023.ijcnlp-main.20"},{"key":"ref_23","unstructured":"Wang, Y., Zhong, W., Li, L., Mi, F., Zeng, X., Huang, W., Shang, L., Jiang, X., and Liu, Q. (2023). Aligning large language models with human: A survey. arXiv."},{"key":"ref_24","unstructured":"Shen, T., Jin, R., Huang, Y., Liu, C., Dong, W., Guo, Z., Wu, X., Liu, Y., and Xiong, D. (2023). Large language model alignment: A survey. arXiv."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/13\/9\/232\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:56:19Z","timestamp":1760111779000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/13\/9\/232"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,14]]},"references-count":24,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2024,9]]}},"alternative-id":["computers13090232"],"URL":"https:\/\/doi.org\/10.3390\/computers13090232","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,14]]}}}