TrafficSafetyGPT: Tuning a Pre-trained Large Language Model to a Domain-Specific Expert in Transportation Safety
This work addresses the need for specialized AI expertise in transportation safety, offering a domain-specific solution that is incremental in nature.
The paper tackles the suboptimal performance of large language models in transportation safety tasks by introducing TrafficSafetyGPT, a fine-tuned LLAMA-based model using a specialized dataset, achieving improved accuracy in domain-specific responses.
Large Language Models (LLMs) have shown remarkable effectiveness in various general-domain natural language processing (NLP) tasks. However, their performance in transportation safety domain tasks has been suboptimal, primarily attributed to the requirement for specialized transportation safety expertise in generating accurate responses [1]. To address this challenge, we introduce TrafficSafetyGPT, a novel LLAMA-based model, which has undergone supervised fine-tuning using TrafficSafety-2K dataset which has human labels from government produced guiding books and ChatGPT-generated instruction-output pairs. Our proposed TrafficSafetyGPT model and TrafficSafety-2K train dataset are accessible at https://github.com/ozheng1993/TrafficSafetyGPT.