PPDL: LLM-Based Flows as Probabilistic Programs
Summary
This paper introduces PPDL, a probabilistic language for programming LLM-based flows that enables developers to quantify and propagate uncertainty throughout applications, with experimental and case studies on theorem proving.
View Cached Full Text
Cached at: 08/07/26, 07:48 AM
# PPDL: LLM-Based Flows as Probabilistic Programs Source: [https://arxiv.org/abs/2608.05234](https://arxiv.org/abs/2608.05234) [View PDF](https://arxiv.org/pdf/2608.05234) > 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 trust the results\. This paper introduces a probabilistic language for programming LLM\-based flows\. It enables developers to quantify and propagate uncertainty throughout the application's flow, and experiment with different inference scaling techniques without adding a single line of code beyond the flow's logic\. We present an experimental study to demonstrate this capability, and a case study building a theorem proving agent for the Rocq theorem prover\. ## Submission history From: Guillaume Baudart \[[view email](https://arxiv.org/show-email/b29d9212/2608.05234)\] **\[v1\]**Wed, 5 Aug 2026 13:37:25 UTC \(115 KB\)
Similar Articles
FlowEdit: Information-Theoretic Control of LLM Reasoning Flows for Ill-posed Problems Involving Conflicts
FlowEdit is a novel framework that uses information-theoretic principles to regulate internal reasoning flows in LLMs, enabling them to generate multiple alternative responses in a single pass for ill-posed problems with conflicting conditions. Experiments show 68% improvement in exact-set-match accuracy and 24% boost in response informativeness over leading proprietary models.
SPL: Orchestrating Workflows with Declarative Deterministic-Probabilistic Composition
SPL (Structured Prompt Language) is a declarative language that unifies deterministic and probabilistic computation modes for LLM workflows, enabling specification of computations that run across local and cloud nodes. It includes an extensive cookbook and experimental validation.
RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization
This paper introduces RLearner-LLM, a framework using Hybrid-DPO to balance logical correctness and fluency in LLM-generated explanations, achieving significant NLI entailment improvements across multiple domains and base models while mitigating the verbosity bias of standard preference signals.
Can recurring LLM traces be synthesized into deterministic pipelines of typed ML and NLP operators? [D]
The article investigates whether recurring LLM workloads can be replaced by automatically synthesized deterministic pipelines of typed ML/NLP operators, and asks for feedback on feasibility and approaches.
Managing Uncertainty in LLM-Generated Procedural Knowledge for Virtual Laboratory Planning
This paper presents a prototype framework for managing uncertainty in LLM-generated procedural knowledge for virtual laboratory planning, using structured domain representations to repair uncertain procedural steps.