LLMs for Argument Mining: Detection, Extraction, and Relationship Classification of pre-defined Arguments in Online Comments

TL;DR

This paper evaluates the effectiveness of large language models in automatically detecting, extracting, and classifying arguments in online comments on controversial topics, highlighting their strengths and limitations.

Contribution

It provides a comprehensive assessment of four state-of-the-art LLMs on argument mining tasks in online comments, revealing their performance and challenges.

Findings

Strong performance of large, fine-tuned LLMs on argument tasks

Systematic shortcomings on long, nuanced, and emotionally charged comments

High environmental cost associated with model training and inference

Abstract

Automated large-scale analysis of public discussions around contested issues like abortion requires detecting and understanding the use of arguments. While Large Language Models (LLMs) have shown promise in language processing tasks, their performance in mining topic-specific, pre-defined arguments in online comments remains underexplored. We evaluate four state-of-the-art LLMs on three argument mining tasks using datasets comprising over 2,000 opinion comments across six polarizing topics. Quantitative evaluation suggests an overall strong performance across the three tasks, especially for large and fine-tuned LLMs, albeit at a significant environmental cost. However, a detailed error analysis revealed systematic shortcomings on long and nuanced comments and emotionally charged language, raising concerns for downstream applications like content moderation or opinion analysis. Our results highlight both the promise and current limitations of LLMs for automated argument analysis in online comments.