LatentPrompt:在潜在空间中优化提示词
LatentPrompt: Optimizing Promts in Latent Space
AI总结:
LatentPrompt提出在潜在空间中自动优化提示词的框架,无需人工规则,仅需黑盒访问LLM,在情感分类任务上提升约3%准确率。
摘要:
近期研究表明,为大型语言模型(LLM)优化提示词可以显著提升任务性能,然而许多优化技术依赖于启发式方法或人工探索。我们提出了LatentPrompt,一个与模型无关的提示词优化框架,它利用潜在语义空间自动生成、评估和优化候选提示词,无需手工制定的规则。从一组种子提示词开始,我们的方法将其嵌入到连续的潜在空间中,并系统地探索该空间以识别能够最大化任务特定性能的提示词。在Financial PhraseBank情感分类基准的概念验证研究中,LatentPrompt在一次优化循环后,将分类准确率提升了约3个百分点。该框架具有广泛的适用性,仅需对LLM的黑盒访问和自动评估指标,适用于多种领域和任务。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。