In plain words: Twenty-six simple rules for phrasing questions to chatbots, meant to make writing prompts easier and to show how models of different sizes respond. Tests on several open and commercial models showed the rules improved answers over ordinary prompts.
Abstract · Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4
This paper introduces 26 guiding principles designed to streamline the process of querying and prompting large language models. Our goal is to simplify the underlying concepts of formulating questions for various scales of large language models, examining their abilities, and enhancing user comprehension on the behaviors of different scales of large language models when feeding into different prompts. Extensive experiments are conducted on LLaMA-1/2 (7B, 13B and 70B), GPT-3.5/4 to verify the effectiveness of the proposed principles on instructions and prompts design. We hope that this work can provide a better guide for researchers working on the prompting of large language models. Project page is available at https://github.com/VILA-Lab/ATLAS.
Sondos Mahmoud Bsharat, Aidar Myrzakhan, Zhiqiang Shen
arXiv:2312.16171 · cs.CL, cs.AI · submitted Dec 26, 2023 · updated Jan 18, 2024
abstract · pdf · html · Github at: https://github.com/VILA-Lab/ATLAS
the fact that adding this to a prompt gets a better response really exemplifies how prompting as it is today is a problem to be solved rather than an engineering discipline