Are Large Language Models Reliable Argument Quality Annotators?

TL;DR

This paper investigates the use of large language models as automated annotators for argument quality, finding they can produce consistent assessments that align well with human experts, thereby improving annotation reliability.

Contribution

The study demonstrates that LLMs can effectively serve as argument quality annotators, enhancing annotation consistency and agreement with human experts.

Findings

LLMs show moderately high agreement with human experts on argument quality.

Using LLMs as annotators improves overall annotation agreement.

LLMs can streamline argument dataset evaluation processes.

Abstract

Evaluating the quality of arguments is a crucial aspect of any system leveraging argument mining. However, it is a challenge to obtain reliable and consistent annotations regarding argument quality, as this usually requires domain-specific expertise of the annotators. Even among experts, the assessment of argument quality is often inconsistent due to the inherent subjectivity of this task. In this paper, we study the potential of using state-of-the-art large language models (LLMs) as proxies for argument quality annotators. To assess the capability of LLMs in this regard, we analyze the agreement between model, human expert, and human novice annotators based on an established taxonomy of argument quality dimensions. Our findings highlight that LLMs can produce consistent annotations, with a moderately high agreement with human experts across most of the quality dimensions. Moreover, we show that using LLMs as additional annotators can significantly improve the agreement between annotators. These results suggest that LLMs can serve as a valuable tool for automated argument quality assessment, thus streamlining and accelerating the evaluation of large argument datasets.