ProSwitch: Knowledge-Guided Instruction Tuning to Switch Between Professional and Non-Professional Responses

TL;DR

ProSwitch is a novel method that enables large language models to switch between professional and non-professional responses by leveraging domain and style knowledge during instruction tuning, improving response style control.

Contribution

It introduces a three-phase approach for training LLMs to effectively switch response styles using knowledge-guided instruction tuning, which outperforms existing models in style discrimination.

Findings

ProSwitch outperforms baseline models in style switching accuracy.

The approach effectively discriminates between professional and non-professional responses.

Knowledge-guided tuning enhances the model's ability to control response style.

Abstract

Large Language Models (LLMs) have demonstrated efficacy in various linguistic applications, including question answering and controlled text generation. However, studies into their ability to switch between opposite styles of responses in professional domains remain underexplored. This study introduces a novel approach, named ProSwitch, which enables a language model to switch between professional and non-professional answers, by tuning and evaluating through the guidance of domain and style knowledge. ProSwitch unfolds in three phases: LLM-augmented preparation to collect domain knowledge and QA pairs, instruction tuning to optimize LLMs with multiple levels of knowledge, and comprehensive evaluation to assess both style discrimination and reference-based quality of the generated text. Comparative analysis of ProSwitch against general and specialized LLMs reveals that our approach outperforms baselines in switching between professional and non-professional responses.