Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems

TL;DR

This paper introduces a multi-objective hyperparameter optimization method for RAG and LLM systems, improving cost, latency, safety, and alignment, and demonstrating superior performance over baselines on new benchmarks.

Contribution

It presents the first multi-objective Bayesian optimization approach for tuning entire RAG and LLM systems across multiple conflicting objectives.

Findings

Bayesian optimization outperforms baseline methods

Achieves better Pareto fronts on RAG benchmarks

Highlights task-specific and objective-specific configuration nuances

Abstract

While Retrieval Augmented Generation (RAG) has emerged as a popular technique for improving Large Language Model (LLM) systems, it introduces a large number of choices, parameters and hyperparameters that must be made or tuned. This includes the LLM, embedding, and ranker models themselves, as well as hyperparameters governing individual RAG components. Yet, collectively optimizing the entire configuration in a RAG or LLM system remains under-explored - especially in multi-objective settings - due to intractably large solution spaces, noisy objective evaluations, and the high cost of evaluations. In this work, we introduce the first approach for multi-objective parameter optimization of cost, latency, safety and alignment over entire LLM and RAG systems. We find that Bayesian optimization methods significantly outperform baseline approaches, obtaining a superior Pareto front on two new RAG benchmark tasks. We conclude our work with important considerations for practitioners who are designing multi-objective RAG systems, highlighting nuances such as how optimal configurations may not generalize across tasks and objectives.