Design and Implementation of Large Language Model-Based Inference Pipeline for Fire Investigation

Checked 30 Sept 2026. Non-commercial or no-derivatives license: full text kept internally; only metadata and abstract are indexed and used.

This study designed and implemented an on-premises generative artificial intelligence (AI)-based fire investigation support pipeline to effectively utilize unstructured fire incident overview information. Existing systems rely on structured fields and keyword-based searches, making it difficult to reflect the contextual and structural similarities in narrative overviews. To overcome these limitations, this study proposes an integrated pipeline comprising text preprocessing, similar case retrieval and selection, large language model (LLM)-based inference of ignition factors, report generation, and result evaluation. In the preprocessing stage, sentence correction and summarization are performed to reduce the variation in expressions while preserving the core meaning. Fire-investigation-related keywords are extracted and used as search queries. In the similar case retrieval stage, semantic and keyword-based searches are combined to improve accuracy and contextual understanding. Subsequently, the retrieved cases are selected based on the structural consistency of the incident components, thereby deriving cases suitable for onsite fire investigation. Experimental results show that the proposed approach addresses the problems of similar case retrieval that cannot be resolved by conventional methods and improves the accuracy and consistency of LLM-based fire-cause inference.

• Hybrid retrieval that combines vector or semantic search with keyword matching or knowledge-graph structure appears independently in fire investigation (Choi & Cho 2026), smart manufacturing (Wan et al. 2025), and biomedicine (Matsumoto et al. 2024), suggesting a convergent design pattern for making domain RAG systems reliable. Trace →

• RAG reliability and evaluation