Work

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

Year: 2024

Type: article

Abstract: 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.

Source: OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)

Author: Agarwal, Vivek [Idaho National Laboratory]; Reeves, Thomas Earl [Idaho National Laboratory]; Walker, Cody McBroom [Idaho National Laboratory]; Lin, Linyu [Idaho National Laboratory]

Institution: Idaho National Laboratory

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: U.S. Department of Energy, Battelle

OpenAlex ID: W4402703738

FWCI:

Cites:

Cited by:

Related to: 10