Exploring LLMs and RAG for Plausible and Explainable Material Prediction of Vehicle Components

RESUMO

In this work, we explore whether LLMs can accurately predict and explain plausible materials for vehicle components such as brake discs or fuel injectors without requiring extensive fine-tuning. We test and evaluate three approaches: a standard generative LLM baseline, a single-pass Retrieval-Augmented Generation (RAG) approach, and an iterative Chain-of-Verification (CoVe) variant. For retrieval, we rely on publicly available data using a domain-filtered Wikipedia corpus. Since no gold standard exists for this task, we develop a custom web-based annotation tool supporting crucial functions for structured domain expert evaluation. LLM-based generation substantially outperforms prior work, which is not further surpassed by the tested RAG approaches. Our results surface remaining challenges for RAG-based systems: hyperparameter optimization, the availability of high-quality, legally accessible domain corpora, and expert evaluation study design.