pith. sign in

arxiv: 2410.10852 · v1 · pith:XSCIJATRnew · submitted 2024-10-06 · 💻 cs.CL · cs.AI

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

Connor Walker , Callum Rothon , Koorosh Aslansefat , Yiannis Papadopoulos , Nina Dethlefs This is my paper
classification 💻 cs.CL cs.AI
keywords agentalarmapproachchatgpt-4detectionlanguagelargemaintenance
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A Comparative Benchmark of Large Language Models for Labelling Wind Turbine Maintenance Logs

    cs.CL 2025-09 unverdicted novelty 4.0

    Introduces a public benchmarking framework for LLMs on wind turbine maintenance log classification, evaluates multiple models, and recommends human-in-the-loop use due to imperfect accuracy and variable calibration.

  2. Bayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on Multi-Hop Question Answering

    cs.AI 2026-07 unverdicted novelty 3.0

    The study applies Bayesian uncertainty propagation to agentic RAG pipelines on StrategyQA and HotpotQA, reporting better discrimination on HotpotQA than on StrategyQA using standard calibration and selective-predictio...