用大模型检测海上风电运维中的虚假和危险输出，提升维修建议安全性
SafeLLM: Domain-Specific Safety Monitoring for Large Language Models: A Case Study of Offshore Wind Maintenance
- 结合统计距离计算，识别大模型生成的幻觉与不安全内容
- 在测试中有效过滤了30%以上的不安全输出
- 适合需要高可靠性的工业安全场景，如能源运维
海上风电行业正快速扩张，导致运维成本上升。智能报警系统有望实现故障与异常的快速发现，从而减少资源浪费和计划内/外停机时间。本文提出一种基于大语言模型的专用对话代理，通过统计方法计算句间距离，用于检测和过滤幻觉及不安全输出。该方法可提升对报警序列的解读能力，并生成更安全的维修建议。初步实验使用ChatGPT-4生成的测试语句进行验证，结果表明该方法能有效识别并过滤不安全内容。论文也讨论了仅依赖ChatGPT-4的局限性，以及通过专用海上风电数据集微调以进一步提升性能的潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。