让AI提示词既高效又可读，解决传统优化方法生成乱码的问题。
BayesPrompt: human readable prompts that make sense
- 将提示词优化转化为贝叶斯后验推断，提升可读性
- 在真实数据集上显著优于现有方法，多指标表现更优
- 适合需要清晰、可解释提示词的开发者和研究人员
重构能引导大模型产生期望回答或行为的提示词是一个开放且重要的研究课题。现有基于最小化答案困惑度的优化方法，常产生无法理解的伪提示（pseudoprompts），缺乏人类可读性。我们指出这是提示词优化任务固有病态所致。通过将该任务重新建模为提示词的贝叶斯后验推断，提出一种高效采样算法，生成在困惑度上高效且对人可读的提示词。在真实数据集上的对比实验表明，该方法在多个指标上均显著优于当前最先进方法。
原文摘要 · Abstract (English)
Reconstructing prompts that can elicit a desired answer or behaviour in an LLM is an open and important research topic. Optimisation methods which aim at minimising the perplexity of a given answer, however, consistently yield so-called pseudoprompts, unintelligible strings of tokens which can lack human interpretability. We argue that this is a consequence of the ill-posedness of the prompt optimisation task. By reframing the task as a Bayesian posterior inference over prompts, we propose an efficient algorithm to sample prompts which are both efficient (in terms of perplexity) and human readable. We compare our approach with state of the art alternatives showing on a real data set a marked improvement over a range of metrics.
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。