RA-CFGPT:Chinese financial assistant with retrieval-augmented large language model  

作　　者：Jiangtong LI Yang LEI Yuxuan BIAN Dawei CHENG Zhijun DING Changjun JIANG 

机构地区：[1]Department of Computer Science and Technology,Tongji University,Shanghai 201804,China [2]Shanghai Artificial Intelligence Laboratory,Shanghai 200030,China

出　　处：《Frontiers of Computer Science》2024年第5期239-241,共3页计算机科学前沿（英文版）

基　　金：The work was supported by the National Key R&D Program of China(2022YFB4501704);the Shanghai Science and Technology InnovationAction PlanProject(22YS1400600 and 22511100700)。

摘　　要：Retrieval-Augmented Generation(RAG)enhances the generative capacity of Large Language Models(LLMs)by appending retrieved documents to the current context.This approach has shown success in reading comprehension[1]and language modeling[2].RAG assumes the intent is in the input query,which can be expanded with a task description.However,in the financial domain,queries often span multiple sectors,challenging the ability of retrieval phase to adequately inform the generation phase.

关 键 词：GENERATIVE expanded assume 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]