Saved in:
Bibliographic Details
Main Authors: Austin, Derek, Chartock, Elliott
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.12865
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929425329684480
author Austin, Derek
Chartock, Elliott
author_facet Austin, Derek
Chartock, Elliott
contents Prompt engineering for large language models (LLMs) is often a manual time-intensive process that involves generating, evaluating, and refining prompts iteratively to ensure high-quality outputs. While there has been work on automating prompt engineering, the solutions generally are either tuned to specific tasks with given answers or are quite costly. We introduce GRAD-SUM, a scalable and flexible method for automatic prompt engineering that builds on gradient-based optimization techniques. Our approach incorporates user-defined task descriptions and evaluation criteria, and features a novel gradient summarization module to generalize feedback effectively. Our results demonstrate that GRAD-SUM consistently outperforms existing methods across various benchmarks, highlighting its versatility and effectiveness in automatic prompt optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2407_12865
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GRAD-SUM: Leveraging Gradient Summarization for Optimal Prompt Engineering
Austin, Derek
Chartock, Elliott
Computation and Language
Artificial Intelligence
Prompt engineering for large language models (LLMs) is often a manual time-intensive process that involves generating, evaluating, and refining prompts iteratively to ensure high-quality outputs. While there has been work on automating prompt engineering, the solutions generally are either tuned to specific tasks with given answers or are quite costly. We introduce GRAD-SUM, a scalable and flexible method for automatic prompt engineering that builds on gradient-based optimization techniques. Our approach incorporates user-defined task descriptions and evaluation criteria, and features a novel gradient summarization module to generalize feedback effectively. Our results demonstrate that GRAD-SUM consistently outperforms existing methods across various benchmarks, highlighting its versatility and effectiveness in automatic prompt optimization.
title GRAD-SUM: Leveraging Gradient Summarization for Optimal Prompt Engineering
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2407.12865