PLHF: Prompt Optimization with Few-Shot Human Feedback

TL;DR

PLHF is a prompt optimization framework that uses minimal human feedback and an evaluator module to improve large language model prompts, especially when output quality metrics are hard to define.

Contribution

It introduces a novel few-shot prompt optimization method leveraging human feedback and an evaluator module, reducing feedback rounds needed.

Findings

PLHF outperforms previous prompt grading strategies.

Requires only one round of human feedback.

Effective on both public and industrial datasets.

Abstract

Automatic prompt optimization frameworks are developed to obtain suitable prompts for large language models (LLMs) with respect to desired output quality metrics. Although existing approaches can handle conventional tasks such as fixed-solution question answering, defining the metric becomes complicated when the output quality cannot be easily assessed by comparisons with standard golden samples. Consequently, optimizing the prompts effectively and efficiently without a clear metric becomes a critical challenge. To address the issue, we present PLHF (which stands for "P"rompt "L"earning with "H"uman "F"eedback), a few-shot prompt optimization framework inspired by the well-known RLHF technique. Different from naive strategies, PLHF employs a specific evaluator module acting as the metric to estimate the output quality. PLHF requires only a single round of human feedback to complete the entire prompt optimization process. Empirical results on both public and industrial datasets show that PLHF outperforms prior output grading strategies for LLM prompt optimizations.