SparkRA: A Retrieval-Augmented Knowledge Service System Based on Spark Large Language Model
Dayong Wu, Jiaqi Li, Baoxin Wang, Honghong Zhao, Siyuan Xue, Yanjie Yang, Zhijun Chang, Rui Zhang
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.
BibTeX
@inproceedings{wu-etal-2024-sparkra,
title = "{S}park{RA}: A Retrieval-Augmented Knowledge Service System Based on Spark Large Language Model",
author = "Wu, Dayong and
Li, Jiaqi and
Wang, Baoxin and
Zhao, Honghong and
Xue, Siyuan and
Yang, Yanjie and
Chang, Zhijun and
Zhang, Rui and
Qian, Li and
Wang, Bo and
Wang, Shijin and
Zhang, Zhixiong and
Hu, Guoping",
editor = "Hernandez Farias, Delia Irazu and
Hope, Tom and
Li, Manling",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-demo.40/",
doi = "10.18653/v1/2024.emnlp-demo.40",
pages = "382--389"
}