paper-with-me

Papers

A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models

2025-01-07 · Shuyang Wang, Somayeh Moazeni, Diego Klabjan

Designing effective prompts is essential to guiding large language models (LLMs) toward desired responses. Automated prompt engineering aims to reduce reliance on manual effort by streamlining the design, refinement, and optimization of natural language prompts. This paper proposes an optimal learning framework for automated prompt engineering, designed to sequentially identify effective prompt features while efficiently allocating a limited evaluation budget. We introduce a feature-based method to express prompts, which significantly broadens the search space. Bayesian regression is employed to utilize correlations among similar prompts, accelerating the learning process. To efficiently explore the large space of prompt features for a high quality prompt, we adopt the forward-looking Knowledge-Gradient (KG) policy for sequential optimal learning. The KG policy is computed efficiently by solving mixed-integer second-order cone optimization problems, making it scalable and capable of accommodating prompts characterized only through constraints. We demonstrate that our method significantly outperforms a set of benchmark strategies assessed on instruction induction tasks. The results highlight the advantages of using the KG policy for prompt learning given a limited evaluation budget. Our framework provides a solution to deploying automated prompt engineering in a wider range applications where prompt evaluation is costly.

📄 PDF Abstract BibTeX arXiv:2501.03508

Code (0)

등록된 구현이 없습니다.

Tasks

Prompt EngineeringPrompt Learning

Methods 이 논문이 사용한 방법론

ADOPT Please enter a description about the method here
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

PRewrite: Prompt Rewriting with Reinforcement Learning

2024-01-16 · Weize Kong, Spurthi Amba Hombaiah, Mingyang Zhang, Qiaozhu Mei 외

Prompt engineering is critical for the development of LLM-based applications. However, it is usually done manually in a "trial and error" fashion that can be time consuming, ineffective, and sub-optimal. Even for the pro…

Prompt Engineeringreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Dynamic Bayesian Optimization Framework for Instruction Tuning in Partial Differential Equation Discovery

2025-12-31 · Junqi Qu, Yan Zhang, Shangqian Gao, Shibo Li arxiv

Large Language Models (LLMs) show promise for equation discovery, yet their outputs are highly sensitive to prompt phrasing, a phenomenon we term instruction brittleness. Static prompts cannot adapt to the evolving state…

Prompt Engineering

Prompting in the Dark: Assessing Human Performance in Prompt Engineering for Data Labeling When Gold Labels Are Absent

2025-02-16 · Zeyu He, Saniya Naphade, Ting-Hao 'Kenneth' Huang

Millions of users prompt large language models (LLMs) for various tasks, but how good are people at prompt engineering? Do users actually get closer to their desired outcome over multiple iterations of their prompts? The…

Prompt Engineering

DDPT: Diffusion-Driven Prompt Tuning for Large Language Model Code Generation

2025-04-06 · Jinyang Li, Sangwon Hyun, M. Ali Babar

Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation. However, the quality of the generated code is heavily dependent on the structure and composition of the prompts used. Crafting hi…

Code GenerationLanguage ModelingLanguage ModellingLarge Language Model+1

A Machine Learning Approach for Emergency Detection in Medical Scenarios Using Large Language Models

2024-12-20 · Ferit Akaybicen, Aaron Cummings, Lota Iwuagwu, Xinyue Zhang 외

The rapid identification of medical emergencies through digital communication channels remains a critical challenge in modern healthcare delivery, particularly with the increasing prevalence of telemedicine. This paper p…

Prompt Engineering