# An LLM-Based System for Argument Mining

arXiv: https://arxiv.org/abs/2605.13793 · HTML: https://mlsanity.com/paper/2605.13793/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 39 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 9 of 9)

- [Parsing Argumentation Structures in Persuasive Essays](https://mlsanity.com/paper/1604.07370/) (2016)
- [Large Language Models in Argument Mining: A Survey](https://mlsanity.com/paper/2506.16383/) (2025)
- [Unsupervised Expressive Rules Provide Explainability and Assist Human Experts Grasping New Domains](https://mlsanity.com/paper/2010.09459/) (2020)
- [Which Side Are You On? A Multi-task Dataset for End-to-End Argument Summarisation and Evaluation](https://mlsanity.com/paper/2406.03151/) (2024)
- [Dissecting Content and Context in Argumentative Relation Analysis](https://mlsanity.com/paper/1906.03338/) (2019)
- [Do Emotions Really Affect Argument Convincingness? A Dynamic Approach with LLM-based Manipulation Checks](https://mlsanity.com/paper/2503.00024/) (2025)
- [Chain of Stance: Stance Detection with Large Language Models](https://mlsanity.com/paper/2408.04649/) (2024)
- [Assessing Good, Bad and Ugly Arguments Generated by ChatGPT: a New Dataset, its Methodology and Associated Tasks](https://mlsanity.com/paper/2406.15130/) (2024)
- [Exploring the Potential of Large Language Models for Estimating the Reading Comprehension Question Difficulty](https://mlsanity.com/paper/2502.17785/) (2025)

## Abstract (arXiv)

Arguments are a fundamental aspect of human reasoning, in which claims are supported, challenged, and weighed against one another. We present an end-to-end large language model (LLM)-based system for reconstructing arguments from natural language text into abstract argument graphs. The system follows a multi-stage pipeline that progressively identifies argumentative components, selects relevant elements, and uncovers their logical relations. These elements are represented as directed acyclic graphs consisting of two component types (premises and conclusions) and three relation types (support, attack, and undercut). We conduct two complementary experiments to evaluate the system. First, we perform a manual evaluation on arguments drawn from an argumentation theory textbook to assess the system's ability to recover argumentative structure. Second, we conduct a quantitative evaluation on benchmark datasets, allowing comparison with prior work by mapping our outputs to established annotation schemes. Results show that the system can adequately recover argumentative structures and, when adapted to different annotation schemes, achieve reasonable performance across benchmark datasets. These findings highlight the potential of LLM-based pipelines for scalable argument mining.