ByteScience: Bridging Unstructured Scientific Literature and Structured Data with Auto Fine-tuned Large Language Model in Token Granularity

TL;DR

ByteScience is a cloud-based platform utilizing auto fine-tuned LLMs to extract structured scientific data from literature, enabling efficient knowledge synthesis with high accuracy from limited annotations.

Contribution

It introduces ByteScience, a novel platform that automates fine-tuning of LLMs for extracting structured data from scientific texts, addressing domain-specific challenges.

Findings

High accuracy with limited annotated data

Automated workflow for custom model development

Effective extraction of multi-layered scientific information

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 fine-tuned 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.