HELP ME THINK: A Simple Prompting Strategy for Non-experts to Create Customized Content with Models

TL;DR

This paper introduces HELP ME THINK, a straightforward prompting method that guides non-experts in creating customized content by asking relevant questions and using their answers, improving control over language model outputs.

Contribution

The paper presents a simple, general prompting strategy that helps non-experts effectively leverage language models for complex tasks without task-specific tuning.

Findings

Effective across various challenging tasks

Reduces complexity for non-experts in prompt design

Enhances control over generated content

Abstract

Controlling the text generated by language models and customizing the content has been a long-standing challenge. Existing prompting techniques proposed in pursuit of providing control are task-specific and lack generality; this provides overwhelming choices for non-expert users to find a suitable method for their task. The effort associated with those techniques, such as in writing examples, explanations, instructions, etc. further limits their adoption among non-expert users. In this paper, we propose a simple prompting strategy HELP ME THINK where we encourage GPT3 to help non-expert users by asking a set of relevant questions and leveraging user answers to execute the task. We demonstrate the efficacy of our technique HELP ME THINK on a variety of tasks. Specifically, we focus on tasks that are hard for average humans and require significant thinking to perform. We hope our work will encourage the development of unconventional ways to harness the power of large language models.