Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization

TL;DR

SAMMO is a symbolic framework that enables efficient compile-time optimization of complex prompt programs in large language model applications, improving performance across various tasks.

Contribution

Introduces SAMMO, a structure-aware symbolic search method for prompt program optimization, generalizing previous approaches and enhancing complex prompt performance.

Findings

Improves instruction tuning prompt performance

Enhances retrieval augmented generation pipeline tuning

Achieves better prompt compression results

Abstract

In many modern LLM applications, such as retrieval augmented generation, prompts have become programs themselves. In these settings, prompt programs are repeatedly called with different user queries or data instances. A big practical challenge is optimizing such prompt programs. Recent work has mostly focused on either simple prompt programs or assumed that the general structure of a prompt program is fixed. We introduce SAMMO, a framework to perform symbolic prompt program search for compile-time optimizations of prompt programs. SAMMO represents prompt programs on a symbolic level which allows for a rich set of transformations that can be searched over during optimization. We show that SAMMO generalizes previous methods and improves the performance of complex prompts on (1) instruction tuning, (2) RAG pipeline tuning, and (3) prompt compression, across several different LLMs. We make all code available open-source at https://github.com/microsoft/sammo .