Large Language Models in Argument Mining: A Survey

2025-06-19

AI Summary

This paper systematically surveys the application of large language models (LLMs) to argument mining (AM). Addressing core challenges—including task fragmentation, annotation scarcity, difficulty in long-context reasoning, and poor interpretability—we propose the first LLM-driven unified task taxonomy for AM. Methodologically, we integrate prompt engineering, chain-of-thought reasoning, retrieval-augmented generation, and cross-domain adaptation into a multi-level framework spanning data curation, model design, and evaluation protocols. We further introduce a hybrid evaluation paradigm that jointly leverages automated metrics and human judgment. Our analysis clarifies prevailing technical pathways and practical bottlenecks, yielding a cohesive knowledge graph integrating theory, data, models, and evaluation. The resulting framework provides a reproducible, scalable, and principled guide for computational argumentation research.

Technology Category

• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Knowledge Representation and Reasoning: Argumentation
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Argument Mining (AM), a critical subfield of Natural Language Processing (NLP), focuses on extracting argumentative structures from text. The advent of Large Language Models (LLMs) has profoundly transformed AM, enabling advanced in-context learning, prompt-based generation, and robust cross-domain adaptability. This survey systematically synthesizes recent advancements in LLM-driven AM. We provide a concise review of foundational theories and annotation frameworks, alongside a meticulously curated catalog of datasets. A key contribution is our comprehensive taxonomy of AM subtasks, elucidating how contemporary LLM techniques -- such as prompting, chain-of-thought reasoning, and retrieval augmentation -- have reconfigured their execution. We further detail current LLM architectures and methodologies, critically assess evaluation practices, and delineate pivotal challenges including long-context reasoning, interpretability, and annotation bottlenecks. Conclusively, we highlight emerging trends and propose a forward-looking research agenda for LLM-based computational argumentation, aiming to strategically guide researchers in this rapidly evolving domain.

Problem

• Surveying LLM advancements in Argument Mining tasks
• Analyzing LLM techniques for argument structure extraction
• Addressing challenges in interpretability and annotation bottlenecks

Innovation

• Advanced in-context learning for argument mining
• Prompt-based generation techniques in AM
• Robust cross-domain adaptability using LLMs