PDL: A Declarative Prompt Programming Language
Mandana Vaziri, Louis Mandel, Claudio Spiess, Martin Hirzel

TL;DR
This paper introduces PDL, a declarative, data-oriented language based on YAML, designed to simplify prompt programming for large language models, making it more robust and accessible.
Contribution
The paper presents PDL, a novel declarative language that improves prompt control and usability across various LLM platforms and applications.
Findings
PDL supports multiple LLM platforms and models.
It simplifies prompt management and application development.
PDL enhances robustness and reduces brittleness in LLM prompts.
Abstract
Large language models (LLMs) have taken the world by storm by making many previously difficult uses of AI feasible. LLMs are controlled via highly expressive textual prompts and return textual answers. Unfortunately, this unstructured text as input and output makes LLM-based applications brittle. This motivates the rise of prompting frameworks, which mediate between LLMs and the external world. However, existing prompting frameworks either have a high learning curve or take away control over the exact prompts from the developer. To overcome this dilemma, this paper introduces the Prompt Declaration Language (PDL). PDL is a simple declarative data-oriented language that puts prompts at the forefront, based on YAML. PDL works well with many LLM platforms and LLMs. It supports writing interactive applications that call LLMs and tools, and makes it easy to implement common use-cases such as…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsFormal Methods in Verification · Embedded Systems Design Techniques · Real-Time Systems Scheduling
MethodsAttention Is All You Need · Adam · Attention Dropout · Dropout · Weight Decay · Dense Connections · Byte Pair Encoding · BART · Layer Normalization · Residual Connection
