# SafeLLM: Domain-Specific Safety Monitoring for Large Language Models: A Case Study of Offshore Wind Maintenance

arXiv: https://arxiv.org/abs/2410.10852 · HTML: https://mlsanity.com/paper/2410.10852/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 30 references that are in the map.
- First posted on arXiv 6 Oct 2024.

## Builds on (most cited first, 14 of 14)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions](https://mlsanity.com/paper/2309.07875/) (2023)
- [Red-Teaming the Stable Diffusion Safety Filter](https://mlsanity.com/paper/2210.04610/) (2022)
- [Statistical Aspects of Wasserstein Distances](https://mlsanity.com/paper/1806.05500/) (2018)
- [Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models](https://mlsanity.com/paper/2102.02503/) (2021)
- [Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation](https://mlsanity.com/paper/2305.15852/) (2023)
- [SafeText: A Benchmark for Exploring Physical Safety in Language Models](https://mlsanity.com/paper/2210.10045/) (2022)
- [Chainpoll: A high efficacy method for LLM hallucination detection](https://mlsanity.com/paper/2310.18344/) (2023)
- [Weakly Supervised Detection of Hallucinations in LLM Activations](https://mlsanity.com/paper/2312.02798/) (2023)
- [Guidance on the Safety Assurance of Autonomous Systems in Complex Environments (SACE)](https://mlsanity.com/paper/2208.00853/) (2022)
- [Keep your Distance: Determining Sampling and Distance Thresholds in Machine Learning Monitoring](https://mlsanity.com/paper/2207.05078/) (2022)
- [A Deep Learning Framework for Wind Turbine Repair Action Prediction Using Alarm Sequences and Long Short Term Memory Algorithms](https://mlsanity.com/paper/2207.09457/) (2022)

## Built on by (most cited first, 4 of 4)

- [A Comparative Benchmark of Large Language Models for Labelling Wind Turbine Maintenance Logs](https://mlsanity.com/paper/2509.06813/) (2025)
- [Bayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on Multi-Hop Question Answering](https://mlsanity.com/paper/2607.00972/) (2026)
- [Exploratory Semantic Reliability Analysis of Wind Turbine Maintenance Logs using Large Language Models](https://mlsanity.com/paper/2509.22366/) (2025)
- [Seeing the Unseen: Towards Training-Free Inspection for Wind Turbine Blades Using Knowledge-Augmented Vision Language Models](https://mlsanity.com/paper/2510.22868/) (2025)

## Abstract (arXiv)

The Offshore Wind (OSW) industry is experiencing significant expansion, resulting in increased Operations & Maintenance (O&M) costs. Intelligent alarm systems offer the prospect of swift detection of component failures and process anomalies, enabling timely and precise interventions that could yield reductions in resource expenditure, as well as scheduled and unscheduled downtime. This paper introduces an innovative approach to tackle this challenge by capitalising on Large Language Models (LLMs). We present a specialised conversational agent that incorporates statistical techniques to calculate distances between sentences for the detection and filtering of hallucinations and unsafe output. This potentially enables improved interpretation of alarm sequences and the generation of safer repair action recommendations by the agent. Preliminary findings are presented with the approach applied to ChatGPT-4 generated test sentences. The limitation of using ChatGPT-4 and the potential for enhancement of this agent through re-training with specialised OSW datasets are discussed.