Can I read Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves on EtoBox?

Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves by Deng, Yihe; Zhang, Weitong; Chen, Zixiang; Gu, Quanquan is a scholarly article available to read on EtoBox.

What is Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves about?

Misunderstandings arise not only in interpersonal communication but also between humans and Large Language Models (LLMs). Such discrepancies can make LLMs interpret seemingly unambiguous questions in unexpected ways, yielding incorrect responses. While it is widely acknowledged that the quality of a prompt, such as a question, significantly impacts the quality of the response provided by LLMs, a systematic method for crafting questions that LLMs can better comprehend is still underdeveloped. In this paper, we present a method named `Rephrase and Respond' (RaR), which allows LLMs to rephrase and expand questions posed by humans and provide responses in a single prompt. This approach serves as a simple yet effective prompting method for improving performance. We also introduce a two-step variant of RaR, where a rephrasing LLM first rephrases the question and then passes the original and rephrased questions together to a different responding LLM. This facilitates the effective utilization of rephrased questions generated by one LLM with another. Our experiments demonstrate that our methods significantly improve the performance of different models across a wide range to tasks. We furth

Author

Deng, Yihe; Zhang, Weitong; Chen, Zixiang; Gu, Quanquan

Published

2023

Language

EN