PPDL：将基于 LLM 的流程作为概率程序

AI 摘要

arXiv 论文提出 PPDL，一种用于编程基于 LLM 流程的概率语言，使开发者能够量化并传播整个应用流程中的不确定性，并无需修改流程逻辑即可实验不同的推理扩展技术。实验研究展示了该能力，案例研究构建了一个用于 Rocq 定理证明器的代理。

正文节选

Computer Science > Machine Learning Title:PPDL: LLM-Based Flows as Probabilistic Programs View PDF Abstract:Building reliable applications that leverage large language models (LLMs) remains a significant challenge. While LLMs offer impressive capabilities across diverse tasks, their outputs often lack accuracy and provide no clear measure of confidence. This uncertainty compounds in flows of multiple calls to LLMs and other tools, making it difficult for developers and end-users to t

发布时间：2026-08-07 12:00

抓取时间：2026-08-07 14:19

来源机构：arXiv