【Proposal】RBPA: Retrieval-Augmented-Generation based personal investment assistant
Keywords: RAG; Investment Assitant; Personal data
Abstract: Large language models (LLMs) have made significant strides in recent years, with their capabilities being harnessed across a multitude of industries for various applications. These models, with their vast parameter counts, are designed to handle complex tasks and data, offering enhanced expressiveness and predictive performance.
Although LLMs can grasp basic world knowledge, they cannot be directly applied to financial markets in dynamic games. The influencing factors of the financial market are complex, from macro to micro and involve a wide range of aspects, and the analysis of the financial market needs to establish a professional knowledge base in the financial field, including basic professional knowledge, logical chain knowledge, and related network knowledge.
Retrieval-Augmented Generation (RAG) is a groundbreaking approach that marries the capabilities of large language models with the precision of information retrieval from reliable database. By leveraging a vast knowledge base, RAG enables the generation of highly accurate, relevant, and timely responses, making it an ideal technology for a personal investment assistant, under which circumstances lots of professional data and personal data are required.
Submission Number: 14
Loading