LatentPrompt: Optimizing Promts in Latent Space

TL;DR

LatentPrompt is a framework that optimizes prompts in a latent semantic space to improve large language model performance without manual rule crafting, demonstrated on sentiment analysis.

Contribution

It introduces a model-agnostic latent space approach for automatic prompt optimization, reducing reliance on heuristics and manual tuning.

Findings

Increased classification accuracy by ~3% on Financial PhraseBank.

Works with black-box LLMs and automatic evaluation metrics.

Applicable across diverse domains and tasks.

Abstract

Recent advances have shown that optimizing prompts for Large Language Models (LLMs) can significantly improve task performance, yet many optimization techniques rely on heuristics or manual exploration. We present LatentPrompt, a model-agnostic framework for prompt optimization that leverages latent semantic space to automatically generate, evaluate, and refine candidate prompts without requiring hand-crafted rules. Beginning with a set of seed prompts, our method embeds them in a continuous latent space and systematically explores this space to identify prompts that maximize task-specific performance. In a proof-of-concept study on the Financial PhraseBank sentiment classification benchmark, LatentPrompt increased classification accuracy by approximately 3 percent after a single optimization cycle. The framework is broadly applicable, requiring only black-box access to an LLM and an automatic evaluation metric, making it suitable for diverse domains and tasks.