Home // INTERNET 2024, The Sixteenth International Conference on Evolving Internet // View article

OKLLM: Online Knowledge Search for LLM Innovations

Authors:
Huan Chen
Andy Donald

Keywords: Ethical AI, LLMs, Knowledge Graph Generation, eXAI, Bias Detection, Transfer Learning.

Abstract:
Nowadays, a breakthrough era in online content discovery and search is being ushered in by the increased availability of Large Language Models (LLMs). However, LLMs are resource and computational-intensive. Additionally, Artificial Intelligence (AI) generated material can occasionally contain bias or false information. With our proposed framework, Online Knowledge Search for Large Language Models (OKLLM), we seek to fill these gaps through the use of knowledge distillation, knowledge graph generation and verification, bias detection, and transfer learning via the development of three distinct components. The first component will concentrate on employing knowledge distillation to handle bias detection tasks in order to enhance search results and lessen computationally taxing tasks. The usage of the knowledge graph to solve the hallucination phenomenon to improve search results will be the focus of the second component, and the third component will make it possible to handle the explainability challenge by utilizing information such as the path gathered from the knowledge graph and visualizing it, thus enhancing the search results output. The intention is to present these components using open-source principles.

Pages: 39 to 41

Copyright: Copyright (c) IARIA, 2024

Publication date: March 10, 2024

Published in: conference

ISSN: 2308-443X

ISBN: 978-1-68558-133-6

Location: Athens, Greece

Dates: from March 10, 2024 to March 14, 2024