Golden-Retriever: High-Fidelity Agentic Retrieval Augmented Generation for Industrial Knowledge Base

TL;DR

Golden-Retriever enhances retrieval-augmented generation for industrial knowledge bases by incorporating a reflection-based question augmentation step, improving document retrieval accuracy in domain-specific contexts.

Contribution

It introduces a reflection-based question augmentation method that clarifies jargon, improving retrieval accuracy in domain-specific RAG frameworks.

Findings

Outperforms baseline methods on domain-specific QA tasks.

Improves retrieval accuracy by clarifying jargon and abbreviations.

Demonstrates robustness across multiple open-source LLMs.

Abstract

This paper introduces Golden-Retriever, designed to efficiently navigate vast industrial knowledge bases, overcoming challenges in traditional LLM fine-tuning and RAG frameworks with domain-specific jargon and context interpretation. Golden-Retriever incorporates a reflection-based question augmentation step before document retrieval, which involves identifying jargon, clarifying its meaning based on context, and augmenting the question accordingly. Specifically, our method extracts and lists all jargon and abbreviations in the input question, determines the context against a pre-defined list, and queries a jargon dictionary for extended definitions and descriptions. This comprehensive augmentation ensures the RAG framework retrieves the most relevant documents by providing clear context and resolving ambiguities, significantly improving retrieval accuracy. Evaluations using three open-source LLMs on a domain-specific question-answer dataset demonstrate Golden-Retriever's superior performance, providing a robust solution for efficiently integrating and querying industrial knowledge bases.