Are Large Language Models Reliable Argument Quality Annotators?
This addresses the problem of inconsistent and expertise-dependent argument quality assessment for researchers and practitioners in argument mining, offering a tool to streamline evaluations, though it is incremental in applying existing LLMs to a specific domain.
The paper tackled the challenge of obtaining reliable annotations for argument quality by evaluating state-of-the-art large language models as proxies for human annotators, finding that LLMs achieve moderately high agreement with human experts and can significantly improve inter-annotator agreement.
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.