Extracting Arguments, Not Just Classifying Them: Instruction-Tuned LLMs for Generative Component Detection

2026-09-21

AI Summary

本文提出了一种基于指令调优的大语言模型的新方法ITFACD，将论据成分检测（ACD）转化为生成任务，直接从文本中识别论据，实验表明该方法优于现有系统。

Abstract

Argumentative component detection (ACD) is a core subtask of Argument(ation) Mining (AM) and one of its most challenging aspects, as it requires jointly delimiting argumentative spans and classifying them into components such as claims and premises. While research on this subtask remains relatively limited compared to other AM tasks, most existing approaches formulate it as a simplified sequence labeling problem, component classification, or a pipeline of component segmentation followed by classification. In this paper, we propose ITFACD, a novel approach based on instruction-tuned Large Language Models (LLMs) using compact instruction-based prompts, and reframe ACD as a language generation task, enabling arguments to be identified directly from plain text without relying on pre-segmented components. Experiments on standard benchmarks show that our approach achieves higher performance compared to state-of-the-art systems. To the best of our knowledge, this is one of the first attempts to fully model ACD as a generative task, highlighting the potential of instruction tuning for complex AM problems. Our code and the datasets used are openly available in the following GitHub repository.

Problem

• Argumentative Component Detection
• Argumentation Mining
• Sequence Labeling
• Component Classification
• Language Generation

Innovation

• instruction-tuned LLMs
• generative task
• argumentative component detection
• language generation