@inproceedings{dfda2e9818624023bd0859cf325879ba,
title = "ByteScience: Bridging Unstructured Scientific Literature and Structured Data with Auto Fine-tuned Large Language Model in Token Granularity",
abstract = "Natural Language Processing (NLP) is widely used to supply summarization ability from long context to structured information. However, extracting structured knowledge from scientific text by NLP models remains a challenge because of its domain-specific nature to complex data preprocessing and the granularity of multi-layered device-level information. To address this, we introduce ByteScience, a non-profit cloud-based auto finetuned Large Language Model (LLM) platform, which is designed to extract structured scientific data and synthesize new scientific knowledge from vast scientific corpora. The platform capitalizes on DARWIN, an open-source, fine-tuned LLM dedicated to natural science. The platform was built on Amazon Web Services (AWS) and provides an automated, user-friendly workflow for custom model development and data extraction. The platform achieves remarkable accuracy with only a small amount of well-annotated articles. This innovative tool streamlines the transition from the science literature to structured knowledge and data and benefits the advancements in natural informatics. Demo Video. {\textcopyright} 2024 IEEE.",
keywords = "component, formatting, insert, style, styling",
author = "Tong Xie and Hanzhi Zhang and Shaozhou Wang and Yuwei Wan and Imran Razzak and Chunyu Kit and Wenjie Zhang and Bram Hoex",
year = "2024",
month = dec,
doi = "10.1109/ICDMW65004.2024.00126",
language = "English",
isbn = "9798331530648",
series = "IEEE International Conference on Data Mining Workshops, ICDMW",
publisher = "IEEE Computer Society",
pages = "907--911",
editor = "Yi He and Wassim Hamidouche and Imran Razzak and Hakim Hacid and Maxim Panov",
booktitle = "Proceedings - 24th IEEE International Conference on Data Mining Workshops, ICDMW 2024",
address = "United States",
note = "24th IEEE International Conference on Data Mining Workshops (ICDMW 2024) ; Conference date: 09-12-2024",
}