Thinking Before Speaking: A Role-playing Model with Mindset

TL;DR

This paper introduces a Thinking Before Speaking (TBS) model that enhances Large Language Models' ability to adopt authentic role-specific mindsets and reasoning by augmenting training data with character-specific scenarios and thought processes.

Contribution

The study proposes a novel data augmentation and fine-tuning approach to improve LLMs' role-playing authenticity by incorporating character mindset and beyond-knowledge elements.

Findings

TBS model better emulates role tone and mindset

Enhanced role-specific responses outside the model's knowledge base

Improved consistency with character scenarios

Abstract

Role-playing is an easy task for Large Language Models (LLMs), as they are skilled at simulating human behaviors. Many current studies have enabled LLMs to generate responses in the tone of a specific role by fine-tuning the models or using specialized prompts. However, it is typically easy to recognize when a role is being played by LLMs. These models tend to perform poorly when confronted with knowledge that the assumed role does not possess, or a question that requires the specific experience or logic of the role to answer. To address this problem and make LLMs act more like real roles, we propose a Thinking Before Speaking (TBS) model in this paper. Unlike other studies, we first extend the data based on the character's real-life scenarios and the historical dialogue, supplementing each pair of dialogue with the character's mindset. Then we add few data points that include elements beyond the role's knowledge, and fine-tune the LLMs. This approach can help LLMs adopt the role's thought process and logic, avoiding responses that fall outside the role's knowledge base. We have also prepared a dataset and evaluation metrics to test these capabilities. Experimental results show that our TBS model can better emulate a role in terms of tone, knowledge, and mindset.