# Transformer-Based Models for Automatic Identification of Argument Relations: A Cross-Domain Evaluation

arXiv: https://arxiv.org/abs/2011.13187 · HTML: https://mlsanity.com/paper/2011.13187/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2020.

## Built on by (most cited first, 20 of 20)

- [Can Large Language Models perform Relation-based Argument Mining?](https://mlsanity.com/paper/2402.11243/) (2024)
- [Automatic Debate Evaluation with Argumentation Semantics and Natural Language Argument Graph Networks](https://mlsanity.com/paper/2203.14647/) (2022)
- [Will It Blend? Mixing Training Paradigms & Prompting for Argument Quality Prediction](https://mlsanity.com/paper/2209.08966/) (2022)
- [Computational Argumentation-based Chatbots: a Survey](https://mlsanity.com/paper/2401.03454/) (2024)
- [Efficient argument classification with compact language models and ChatGPT-4 refinements](https://mlsanity.com/paper/2403.15473/) (2024)
- [VivesDebate-Speech: A Corpus of Spoken Argumentation to Leverage Audio Features for Argument Mining](https://mlsanity.com/paper/2302.12584/) (2023)
- [Leveraging Small LLMs for Argument Mining in Education: Argument Component Identification, Classification, and Assessment](https://mlsanity.com/paper/2502.14389/) (2025)
- [An Explainable Framework for Misinformation Identification via Critical Question Answering](https://mlsanity.com/paper/2503.14626/) (2025)
- [LLMs for Argument Mining: Detection, Extraction, and Relationship Classification of pre-defined Arguments in Online Comments](https://mlsanity.com/paper/2505.22956/) (2025)
- [Multi-Task and Multi-Corpora Training Strategies to Enhance Argumentative Sentence Linking Performance](https://mlsanity.com/paper/2109.13067/) (2021)
- [A Cascade Model for Argument Mining in Japanese Political Discussions: the QA Lab-PoliInfo-3 Case Study](https://mlsanity.com/paper/2207.01672/) (2022)
- [Assisted Debate Builder with Large Language Models](https://mlsanity.com/paper/2405.13015/) (2024)
- [A comprehensive study of LLM-based argument classification: from LLAMA through GPT-4o to Deepseek-R1](https://mlsanity.com/paper/2507.08621/) (2025)
- [A comprehensive study of LLM-based argument classification: from Llama through DeepSeek to GPT-5.2](https://mlsanity.com/paper/2603.19253/) (2026)
- [Form Without Function: Agent Social Behavior in the Moltbook Network](https://mlsanity.com/paper/2604.13052/) (2026)
- [Perturbations and Subpopulations for Testing Robustness in Token-Based Argument Unit Recognition](https://mlsanity.com/paper/2209.14780/) (2022)
- [HiLO: High-Level Object Fusion for Autonomous Driving using Transformers](https://mlsanity.com/paper/2506.02554/) (2025)
- [Argument Quality Annotation and Gender Bias Detection in Financial Communication through Large Language Models](https://mlsanity.com/paper/2508.08262/) (2025)
- [Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution](https://mlsanity.com/paper/2607.14905/) (2026)
- [Designing and Analysing Argument Mining Pipelines: Towards a Comprehensive Assessment](https://mlsanity.com/paper/2609.26338/) (2026)

## Abstract (arXiv)

Argument Mining is defined as the task of automatically identifying and extracting argumentative components (e.g., premises, claims, etc.) and detecting the existing relations among them (i.e., support, attack, rephrase, no relation). One of the main issues when approaching this problem is the lack of data, and the size of the publicly available corpora. In this work, we use the recently annotated US2016 debate corpus. US2016 is the largest existing argument annotated corpus, which allows exploring the benefits of the most recent advances in Natural Language Processing in a complex domain like Argument (relation) Mining. We present an exhaustive analysis of the behavior of transformer-based models (i.e., BERT, XLNET, RoBERTa, DistilBERT and ALBERT) when predicting argument relations. Finally, we evaluate the models in five different domains, with the objective of finding the less domain dependent model. We obtain a macro F1-score of 0.70 with the US2016 evaluation corpus, and a macro F1-score of 0.61 with the Moral Maze cross-domain corpus.