Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Style

TL;DR

This paper investigates how different prompts and a Tree-of-Thoughts prompting method can enhance large language models' ability to imitate a specific person's language style, demonstrating that ToT with Llama 3 yields the best results.

Contribution

It introduces a Tree-of-Thoughts prompting approach to improve LLMs' style imitation and demonstrates its effectiveness with Llama 3 in creating personalized conversational AI.

Findings

Llama 3 outperforms other models in style imitation.

Tree-of-Thoughts prompting significantly enhances imitation accuracy.

The method enables style-specific interaction without changing core model parameters.

Abstract

Large language models (LLMs), such as GPT series and Llama series have demonstrated strong capabilities in natural language processing, contextual understanding, and text generation. In recent years, researchers are trying to enhance the abilities of LLMs in performing various tasks, and numerous studies have proved that well-designed prompts can significantly improve the performance of LLMs on these tasks. This study compares the language style imitation ability of three different large language models under the guidance of the same zero-shot prompt. It also involves comparing the imitation ability of the same large language model when guided by three different prompts individually. Additionally, by applying a Tree-of-Thoughts (ToT) Prompting method to Llama 3, a conversational AI with the language style of a real person was created. In this study, three evaluation methods were used to evaluate LLMs and prompts. The results show that Llama 3 performs best at imitating language styles, and that the ToT prompting method is the most effective to guide it in imitating language styles. Using a ToT framework, Llama 3 was guided to interact with users in the language style of a specific individual without altering its core parameters, thereby creating a text-based conversational AI that reflects the language style of the individual.