SparkRA:基于星火大语言模型的检索增强知识服务系统
SparkRA: A Retrieval-Augmented Knowledge Service System Based on Spark Large Language Model
AI总结:
该研究基于讯飞星火大模型开发面向科技文献的SciLit-LLM,构建了具备文献调研、论文阅读、学术写作功能的知识服务系统SparkRA,截至2024年7月底已获超5万注册用户、130万次使用。
摘要:
大语言模型(LLMs)已在各类语言任务中取得显著成果。为提升LLMs在科技文献服务中的表现,我们基于讯飞星火LLM,通过在科技文献上进行预训练和监督微调,开发了科技文献大语言模型SciLit-LLM。此外,我们基于自研的SciLit-LLM提出了知识服务系统Spark Research Assistant(SparkRA)。SparkRA已上线开放使用,提供文献调研、论文阅读和学术写作三大核心功能。截至2024年7月30日,SparkRA已积累超50000名注册用户,总使用次数突破130万次。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。