# Classification of Safety Events at Nuclear Sites using Large Language Models

arXiv: https://arxiv.org/abs/2409.00091 · HTML: https://mlsanity.com/paper/2409.00091/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 10 references that are in the map.
- First posted on arXiv 26 Aug 2024.

## Builds on (most cited first, 4 of 4)

- [Generative AI Text Classification using Ensemble LLM Approaches](https://mlsanity.com/paper/2309.07755/) (2023)
- [Practical Text Classification With Large Pre-Trained Language Models](https://mlsanity.com/paper/1812.01207/) (2018)
- [SHAP values for Explaining CNN-based Text Classification Models](https://mlsanity.com/paper/2008.11825/) (2020)
- [Using Deep Learning to Automate the Detection of Flaws in Nuclear Fuel Channel UT Scans](https://mlsanity.com/paper/2102.13635/) (2021)

## Built on by (most cited first, 2 of 2)

- [Standardizing Intelligence: Aligning Generative AI for Regulatory and Operational Compliance](https://mlsanity.com/paper/2503.04736/) (2025)
- [From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance](https://mlsanity.com/paper/2607.24791/) (2026)

## Abstract (arXiv)

This paper proposes the development of a Large Language Model (LLM) based machine learning classifier designed to categorize Station Condition Records (SCRs) at nuclear power stations into safety-related and non-safety-related categories. The primary objective is to augment the existing manual review process by enhancing the efficiency and accuracy of the safety classification process at nuclear stations. The paper discusses experiments performed to classify a labeled SCR dataset and evaluates the performance of the classifier. It explores the construction of several prompt variations and their observed effects on the LLM's decision-making process. Additionally, it introduces a numerical scoring mechanism that could offer a more nuanced and flexible approach to SCR safety classification. This method represents an innovative step in nuclear safety management, providing a scalable tool for the identification of safety events.