Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4
This work provides a better guide for researchers working on prompting large language models, but it is incremental as it builds on existing prompting techniques.
The paper tackles the problem of querying and prompting large language models by introducing 26 guiding principles to simplify question formulation and enhance user comprehension of model behaviors, with experiments on LLaMA-1/2 and GPT-3.5/4 verifying their effectiveness.
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.