Saved in:
Bibliographic Details
Main Authors: Schneider, Lennart, Wistuba, Martin, Klein, Aaron, Golebiowski, Jacek, Zappella, Giovanni, Merra, Felice Antonio
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.07820
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909633988263936
author Schneider, Lennart
Wistuba, Martin
Klein, Aaron
Golebiowski, Jacek
Zappella, Giovanni
Merra, Felice Antonio
author_facet Schneider, Lennart
Wistuba, Martin
Klein, Aaron
Golebiowski, Jacek
Zappella, Giovanni
Merra, Felice Antonio
contents Optimal prompt selection is crucial for maximizing large language model (LLM) performance on downstream tasks, especially in black-box settings where models are only accessible via APIs. Black-box prompt selection is challenging due to potentially large, combinatorial search spaces, absence of gradient information, and high evaluation cost of prompts on a validation set. We propose HbBoPs, a novel method that combines a structural-aware deep kernel Gaussian Process with Hyperband as a multi-fidelity scheduler to efficiently select prompts. HbBoPs uses embeddings of instructions and few-shot exemplars, treating them as modular components within prompts. This enhances the surrogate model's ability to predict which prompt to evaluate next in a sample-efficient manner. Hyperband improves query-efficiency by adaptively allocating resources across different fidelity levels, reducing the number of validation instances required for evaluating prompts. Extensive experiments across ten diverse benchmarks and three LLMs demonstrate that HbBoPs outperforms state-of-the-art methods in both performance and efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07820
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hyperband-based Bayesian Optimization for Black-box Prompt Selection
Schneider, Lennart
Wistuba, Martin
Klein, Aaron
Golebiowski, Jacek
Zappella, Giovanni
Merra, Felice Antonio
Machine Learning
Artificial Intelligence
Optimal prompt selection is crucial for maximizing large language model (LLM) performance on downstream tasks, especially in black-box settings where models are only accessible via APIs. Black-box prompt selection is challenging due to potentially large, combinatorial search spaces, absence of gradient information, and high evaluation cost of prompts on a validation set. We propose HbBoPs, a novel method that combines a structural-aware deep kernel Gaussian Process with Hyperband as a multi-fidelity scheduler to efficiently select prompts. HbBoPs uses embeddings of instructions and few-shot exemplars, treating them as modular components within prompts. This enhances the surrogate model's ability to predict which prompt to evaluate next in a sample-efficient manner. Hyperband improves query-efficiency by adaptively allocating resources across different fidelity levels, reducing the number of validation instances required for evaluating prompts. Extensive experiments across ten diverse benchmarks and three LLMs demonstrate that HbBoPs outperforms state-of-the-art methods in both performance and efficiency.
title Hyperband-based Bayesian Optimization for Black-box Prompt Selection
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2412.07820