PromptSuite: A Task-Agnostic Framework for Multi-Prompt Generation
This addresses the challenge of robust LLM evaluation for researchers and practitioners, though it is incremental as it builds on existing multi-prompt evaluation concepts.
The paper tackles the problem of unreliable LLM evaluation due to single-prompt sensitivity by introducing PromptSuite, a framework for automatic multi-prompt generation, which provides meaningful variations to support robust evaluation practices.
Evaluating LLMs with a single prompt has proven unreliable, with small changes leading to significant performance differences. However, generating the prompt variations needed for a more robust multi-prompt evaluation is challenging, limiting its adoption in practice. To address this, we introduce PromptSuite, a framework that enables the automatic generation of various prompts. PromptSuite is flexible - working out of the box on a wide range of tasks and benchmarks. It follows a modular prompt design, allowing controlled perturbations to each component, and is extensible, supporting the addition of new components and perturbation types. Through a series of case studies, we show that PromptSuite provides meaningful variations to support strong evaluation practices. All resources, including the Python API, source code, user-friendly web interface, and demonstration video, are available at: https://eliyahabba.github.io/PromptSuite/.