SparkRA: A Retrieval-Augmented Knowledge Service System Based on Spark Large Language Model

TL;DR

This paper introduces SparkRA, a knowledge service system powered by SciLit-LLM, a large language model specialized in scientific literature, offering literature investigation, paper reading, and academic writing functionalities.

Contribution

The paper presents SciLit-LLM, a specialized LLM for scientific literature, and develops SparkRA, an accessible online system with extensive user engagement.

Findings

Over 50,000 registered users as of July 2024

More than 1.3 million total usages

Enhanced scientific literature services with LLM

Abstract

Large language models (LLMs) have shown remarkable achievements across various language tasks.To enhance the performance of LLMs in scientific literature services, we developed the scientific literature LLM (SciLit-LLM) through pre-training and supervised fine-tuning on scientific literature, building upon the iFLYTEK Spark LLM. Furthermore, we present a knowledge service system Spark Research Assistant (SparkRA) based on our SciLit-LLM. SparkRA is accessible online and provides three primary functions: literature investigation, paper reading, and academic writing. As of July 30, 2024, SparkRA has garnered over 50,000 registered users, with a total usage count exceeding 1.3 million.