KnowledgeHub: An End-to-End Tool for Assisted Scientific Discovery
Abstract
Artificial intelligence is rapidly encroaching on the field of service regulation. However, existing AI-based regulation techniques are often tailored to specific application domains and thus are difficult to generalize in an automated manner. This paper presents Horae, a unified specification language for modeling (multimodal) regulation rules across a diverse set of domains. We showcase how Horae facilitates an intelligent service regulation pipeline by further exploiting a fine-tuned large language model named RuleGPT that automates the Horae modeling process, thereby yielding an end-to-end framework for fully automated intelligent service regulation. The feasibility and effectiveness of our framework are demonstrated over a benchmark of various real-world regulation domains. In particular, we show that our open-sourced, fine-tuned RuleGPT with 7B parameters suffices to outperform GPT-3.5 and perform on par with GPT-4o.
Cite
Text
Tanaka et al. "KnowledgeHub: An End-to-End Tool for Assisted Scientific Discovery." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/1039Markdown
[Tanaka et al. "KnowledgeHub: An End-to-End Tool for Assisted Scientific Discovery." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/tanaka2024ijcai-knowledgehub/) doi:10.24963/ijcai.2024/1039BibTeX
@inproceedings{tanaka2024ijcai-knowledgehub,
title = {{KnowledgeHub: An End-to-End Tool for Assisted Scientific Discovery}},
author = {Tanaka, Shinnosuke and Barry, James and Kuruvanthodi, Vishnudev and Moses, Movina and Giammona, Maxwell J. and Herr, Nathan and Elkaref, Mohab and de Mel, Geeth},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2024},
pages = {8815-8819},
doi = {10.24963/ijcai.2024/1039},
url = {https://mlanthology.org/ijcai/2024/tanaka2024ijcai-knowledgehub/}
}