SparkRA: A Retrieval-Augmented Knowledge Service System Based on Spark Large Language Model
This work addresses the need for improved LLM-based tools for researchers and academics in scientific literature services, though it appears incremental as it builds on existing LLMs.
The authors tackled the problem of enhancing large language models (LLMs) for scientific literature services by developing SciLit-LLM through pre-training and fine-tuning on scientific literature, and introduced SparkRA, a knowledge service system with functions like literature investigation and academic writing, which has gained over 50,000 registered users and 1.3 million uses.
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.