ADO: Automatic Data Optimization for Inputs in LLM Prompts

TL;DR

This paper presents ADO, a method for optimizing input data in prompts to improve LLM performance through content engineering and structural reformulation.

Contribution

It introduces a novel two-step approach for input data optimization, focusing on content and structure, to enhance LLM prompt effectiveness.

Findings

Optimized input data improves LLM task performance

Content engineering and reformulation significantly boost results

Open-source code available for replication

Abstract

This study explores a novel approach to enhance the performance of Large Language Models (LLMs) through the optimization of input data within prompts. While previous research has primarily focused on refining instruction components and augmenting input data with in-context examples, our work investigates the potential benefits of optimizing the input data itself. We introduce a two-pronged strategy for input data optimization: content engineering and structural reformulation. Content engineering involves imputing missing values, removing irrelevant attributes, and enriching profiles by generating additional information inferred from existing attributes. Subsequent to content engineering, structural reformulation is applied to optimize the presentation of the modified content to LLMs, given their sensitivity to input format. Our findings suggest that these optimizations can significantly improve the performance of LLMs in various tasks, offering a promising avenue for future research in prompt engineering. The source code is available at https://anonymous.4open.science/r/ADO-6BC5/