Redefining Information Retrieval of Structured Database via Large Language Models

TL;DR

This paper introduces ChatLR, a novel retrieval augmentation framework using Large Language Models as retrievers, significantly improving information retrieval accuracy for structured databases, especially in the financial domain.

Contribution

The paper presents ChatLR, a new LLM-based retrieval framework that enhances retrieval precision and integrates domain-specific fine-tuning for financial question answering.

Findings

Achieves over 98.8% retrieval accuracy.

Effectively addresses user queries in structured databases.

Demonstrates superiority over traditional retriever methods.

Abstract

Retrieval augmentation is critical when Language Models (LMs) exploit non-parametric knowledge related to the query through external knowledge bases before reasoning. The retrieved information is incorporated into LMs as context alongside the query, enhancing the reliability of responses towards factual questions. Prior researches in retrieval augmentation typically follow a retriever-generator paradigm. In this context, traditional retrievers encounter challenges in precisely and seamlessly extracting query-relevant information from knowledge bases. To address this issue, this paper introduces a novel retrieval augmentation framework called ChatLR that primarily employs the powerful semantic understanding ability of Large Language Models (LLMs) as retrievers to achieve precise and concise information retrieval. Additionally, we construct an LLM-based search and question answering system tailored for the financial domain by fine-tuning LLM on two tasks including Text2API and API-ID recognition. Experimental results demonstrate the effectiveness of ChatLR in addressing user queries, achieving an overall information retrieval accuracy exceeding 98.8\%.