LLMs for Argument Mining: Detection, Extraction, and Relationship Classification of pre-defined Arguments in Online Comments
This addresses the problem of automated large-scale analysis of public discussions for applications like content moderation or opinion analysis, but it is incremental as it applies existing LLMs to a specific domain.
The paper evaluated four state-of-the-art LLMs on detecting, extracting, and classifying pre-defined arguments in over 2,000 online comments across six polarizing topics, finding strong overall performance but systematic errors on long, nuanced, and emotionally charged content.
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.