在潜在语义空间中自动优化提示词，提升大模型任务表现
LatentPrompt: Optimizing Promts in Latent Space
- 将提示词映射到连续潜空间，系统搜索最优提示
- 金融文本分类任务准确率提升约3个百分点
- 无需规则设计，适用于多种任务和领域
近期研究表明，优化大语言模型（LLMs）的提示词可显著提升任务性能，但许多优化方法依赖启发式或人工探索。我们提出LatentPrompt，一种模型无关的提示优化框架，利用潜在语义空间自动生成、评估并优化候选提示，无需手工规则。从一组初始提示开始，该方法将其嵌入连续潜空间，并系统探索以寻找最大化任务性能的提示。在金融短语银行（Financial PhraseBank）情感分类基准上的概念验证研究中，经过一次优化周期，分类准确率提升了约3个百分点。该框架通用性强，仅需黑盒访问LLM和自动评估指标，适用于多样任务与领域。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。