Promptile recovers and reuses user prompting strategies for large language models
Promptile: Recovering and Reusing Prompting Strategies from LLM Interaction Histories
Human-Computer Interaction
Summary
People often develop their own ways to talk to large language models (LLMs) to get better answers, but these helpful prompts get scattered across many conversations. The authors found that these prompting methods can be broken down and shared across tasks. They created Promptile, a system that looks at a user's past interactions to find and organize these prompting tricks. Promptile then helps users reuse and adapt these prompts, saving time and getting results closer to what they want.
What this means in practice
- •For software developers: Improve user interfaces by integrating recovered prompting strategies from LLM interaction histories to reduce repetitive input.
- •For customer support teams: Enable faster and more consistent responses by reusing proven prompt templates extracted from past interactions with LLMs.
Authors
Qingyang Wan, Chang Liu, Zhoutong Ye, Chengwen Zhang, Yanru Qian, Zhike Wang, Jie Cai, Chun Yu, Yuanchun Shi
Abstract
As people use large language models (LLMs) over time, they develop their own ways of prompting to achieve desired results. These useful experiences often remain scattered and unorganized across conversations. Yet existing personalization approaches primarily capture user preferences or explicitly defined workflows. Through a formative study, we found that users develop prompting strategies that range from implicit instructions to explicit templates from these experiences. We further find that interaction behaviors provide evidence for these strategies, which can be decomposed and recombined for reuse across tasks. Building on these findings, we present Promptile, a framework that identifies and validates users' prompting strategies from interaction histories. Promptile organizes these strategies into reusable components that can be retrieved, combined, and adapted to users' current tasks. Our evaluation shows that Promptile accurately recovers and reuses these strategies, better aligning model outputs with users' expectations while reducing repetitive prompting effort.