2000 character limit reached
SparkRA: A Retrieval-Augmented Knowledge Service System Based on Spark Large Language Model (2408.06574v1)
Published 13 Aug 2024 in cs.CL
Abstract: 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.
- Dayong Wu (16 papers)
- Jiaqi Li (142 papers)
- Baoxin Wang (15 papers)
- Honghong Zhao (4 papers)
- Siyuan Xue (1 paper)
- Yanjie Yang (2 papers)
- Zhijun Chang (1 paper)
- Rui Zhang (1138 papers)
- Li Qian (43 papers)
- Bo Wang (823 papers)
- Shijin Wang (69 papers)
- Zhixiong Zhang (8 papers)
- Guoping Hu (39 papers)