Persona Knowledge-Aligned Prompt Tuning Method for Online Debate

TL;DR

This paper introduces a novel prompt tuning framework leveraging ChatGPT's capabilities to incorporate audience persona knowledge for improved argument quality assessment in online debates.

Contribution

It is the first to utilize ChatGPT's emergent abilities to inject audience persona knowledge into smaller models for debate analysis.

Findings

Significant performance improvements over existing methods

Effective integration of audience persona knowledge

Demonstrated robustness across datasets

Abstract

Debate is the process of exchanging viewpoints or convincing others on a particular issue. Recent research has provided empirical evidence that the persuasiveness of an argument is determined not only by language usage but also by communicator characteristics. Researchers have paid much attention to aspects of languages, such as linguistic features and discourse structures, but combining argument persuasiveness and impact with the social personae of the audience has not been explored due to the difficulty and complexity. We have observed the impressive simulation and personification capability of ChatGPT, indicating a giant pre-trained language model may function as an individual to provide personae and exert unique influences based on diverse background knowledge. Therefore, we propose a persona knowledge-aligned framework for argument quality assessment tasks from the audience side. This is the first work that leverages the emergence of ChatGPT and injects such audience personae knowledge into smaller language models via prompt tuning. The performance of our pipeline demonstrates significant and consistent improvement compared to competitive architectures.