Sparkra: A Retrieval-augmented Knowledge Service System Based On Spark Large Language Model

Wu Dayong, Li Jiaqi, Wang Baoxin, Zhao Honghong, Xue Siyuan, Yang Yanjie, Chang Zhijun, Zhang Rui, Qian Li, Wang Bo, Wang Shijin, Zhang Zhixiong, Hu Guoping. Arxiv 2024

[Paper]    
Fine Tuning Pretraining Methods RAG Training Techniques

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.

Similar Work