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

08/17/2022
by   Swaroop Mishra, et al.
21

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/05/2022

Can language models learn from explanations in context?

Large language models can perform new tasks by adapting to a few in-cont...
research
09/16/2021

Reframing Instructional Prompts to GPTk's Language

How can model designers turn task instructions into effective prompts fo...
research
08/19/2023

ControlRetriever: Harnessing the Power of Instructions for Controllable Retrieval

Recent studies have shown that dense retrieval models, lacking dedicated...
research
06/03/2023

Guided scenarios with simulated expert personae: a remarkable strategy to perform cognitive work

Large language models (LLMs) trained on a substantial corpus of human kn...
research
04/04/2023

PromptAid: Prompt Exploration, Perturbation, Testing and Iteration using Visual Analytics for Large Language Models

Large Language Models (LLMs) have gained widespread popularity due to th...
research
09/14/2023

ExpertQA: Expert-Curated Questions and Attributed Answers

As language models are adapted by a more sophisticated and diverse set o...
research
07/06/2023

Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts

Many cognitive approaches to well-being, such as recognizing and reframi...

Please sign up or login with your details

Forgot password? Click here to reset