# From Documents to Database: Failure Modes for Industrial Assets

arXiv: https://arxiv.org/abs/2509.17834 · HTML: https://mlsanity.com/paper/2509.17834/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 11 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Builds on (most cited first, 2 of 2)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [FMEA Builder: Expert Guided Text Generation for Equipment Maintenance](https://mlsanity.com/paper/2411.05054/) (2024)

## Abstract (arXiv)

We propose an interactive system using foundation models and user-provided technical documents to generate Failure Mode and Effects Analyses (FMEA) for industrial equipment. Our system aggregates unstructured content across documents to generate an FMEA and stores it in a relational database. Leveraging this tool, the time required for creation of this knowledge-intensive content is reduced, outperforming traditional manual approaches. This demonstration showcases the potential of foundation models to facilitate the creation of specialized structured content for enterprise asset management systems.