Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Improving Reliability of Large Language Models for Nuclear Power Plant Diagnostics Technical Presentation

Conference ·
OSTI ID:2440149

Large Language Models (LLMs) struggle out of the box when answering factually about detailed questions, especially in domains that are sparsely represented in their training data. This causes hallucinations and reduces reliability making it difficult for them to be used in practice. This work shows that using RAG techniques can improve factual accuracy and reliability, allowing for the application of LLMs in specialized areas, even when those areas that aren’t extensively covered in their initial training.

Research Organization:
Idaho National Laboratory (INL), Idaho Falls, ID (United States)
Sponsoring Organization:
58
DOE Contract Number:
AC07-05ID14517
OSTI ID:
2440149
Report Number(s):
INL/EXP-24-79812-Rev000
Country of Publication:
United States
Language:
English