Towards Optimizing a Retrieval Augmented Generation using Large Language Model on Academic Data

TL;DR

This paper evaluates and optimizes Retrieval Augmented Generation (RAG) models for academic data, introducing new techniques and a novel evaluation method to improve domain-specific performance.

Contribution

It presents four optimization techniques for RAG in academic contexts and introduces the RAG Confusion Matrix for better evaluation of configurations.

Findings

Multi-query significantly improves retrieval performance.

Optimizations enhance LLM-based RAG effectiveness in academic data.

Insights into open-source and closed-source LLM integration for RAG.

Abstract

Given the growing trend of many organizations integrating Retrieval Augmented Generation (RAG) into their operations, we assess RAG on domain-specific data and test state-of-the-art models across various optimization techniques. We incorporate four optimizations; Multi-Query, Child-Parent-Retriever, Ensemble Retriever, and In-Context-Learning, to enhance the functionality and performance in the academic domain. We focus on data retrieval, specifically targeting various study programs at a large technical university. We additionally introduce a novel evaluation approach, the RAG Confusion Matrix designed to assess the effectiveness of various configurations within the RAG framework. By exploring the integration of both open-source (e.g., Llama2, Mistral) and closed-source (GPT-3.5 and GPT-4) Large Language Models, we offer valuable insights into the application and optimization of RAG frameworks in domain-specific contexts. Our experiments show a significant performance increase when including multi-query in the retrieval phase.