paper-with-me

Papers

GRAD-SUM: Leveraging Gradient Summarization for Optimal Prompt Engineering

2024-07-12 · Derek Austin, Elliott Chartock

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.

📄 PDF Abstract BibTeX arXiv:2407.12865

Code (0)

등록된 구현이 없습니다.

Tasks

Prompt Engineering

Similar Papers 제목 키워드 기반

Provable optimal transport with transformers: The essence of depth and prompt engineering

2024-10-25 · Hadi Daneshmand

Can we establish provable performance guarantees for transformers? Establishing such theoretical guarantees is a milestone in developing trustworthy generative AI. In this paper, we take a step toward addressing this que…

Prompt Engineering

Learning Optimal Prompt Ensemble for Multi-source Visual Prompt Transfer

2025-04-09 · Enming Zhang, Liwen Cao, Yanru Wu, Zijie Zhao 외

Prompt tuning has emerged as a lightweight adaptation strategy for adapting foundation models to downstream tasks, particularly in resource-constrained systems. As pre-trained prompts have become valuable intellectual as…

Transfer Learning

LLM as a Complementary Optimizer to Gradient Descent: A Case Study in Prompt Tuning

2024-05-30 · Zixian Guo, Ming Liu, Zhilong Ji, Jinfeng Bai 외

Mastering a skill generally relies on both hands-on experience from doers and insightful, high-level guidance by mentors. Will this strategy also work well for solving complex non-convex optimization problems? Here, a co…

Prompt Optimization with Logged Bandit Data

2025-04-03 · Haruka Kiyohara, Daniel Yiming Cao, Yuta Saito, Thorsten Joachims

We study how to use naturally available user feedback, such as clicks, to optimize large language model (LLM) pipelines for generating personalized sentences using prompts. Naive approaches, which estimate the policy gra…

Language ModelingLanguage ModellingLarge Language Model

MAPGD: Multi-Agent Prompt Gradient Descent for Collaborative Prompt Optimization

2025-09-14 · Yichen Han, Yuhang Han, Siteng Huang, Guanyu Liu 외 arxiv

Prompt engineering is crucial for fully leveraging large language models (LLMs), yet most existing optimization methods follow a single trajectory, resulting in limited adaptability, gradient conflicts, and high computat…

Prompt Engineering