# Winning with Less for Low Resource Languages: Advantage of Cross-Lingual English_Persian Argument Mining Model over LLM Augmentation

arXiv: https://arxiv.org/abs/2511.20872 · HTML: https://mlsanity.com/paper/2511.20872/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 44 references that are in the map.
- First posted on arXiv 25 Nov 2025.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Parsing Argumentation Structures in Persuasive Essays](https://mlsanity.com/paper/1604.07370/) (2016)
- [Argumentation Mining in User-Generated Web Discourse](https://mlsanity.com/paper/1601.02403/) (2016)
- [Neural End-to-End Learning for Computational Argumentation Mining](https://mlsanity.com/paper/1704.06104/) (2017)
- [Corpus Wide Argument Mining -- a Working Solution](https://mlsanity.com/paper/1911.10763/) (2019)
- [IAM: A Comprehensive and Large-Scale Dataset for Integrated Argument Mining Tasks](https://mlsanity.com/paper/2203.12257/) (2022)
- [Cross-lingual Argumentation Mining: Machine Translation (and a bit of Projection) is All You Need!](https://mlsanity.com/paper/1807.08998/) (2018)
- [Argument Mining in Data Scarce Settings: Cross-lingual Transfer and Few-shot Techniques](https://mlsanity.com/paper/2407.03748/) (2024)
- [ORCHID: A Chinese Debate Corpus for Target-Independent Stance Detection and Argumentative Dialogue Summarization](https://mlsanity.com/paper/2410.13667/) (2024)
- [Argument Component Classification for Classroom Discussions](https://mlsanity.com/paper/1909.03022/) (2019)
- [Crowdsourcing Argumentation Structures in Chinese Hotel Reviews](https://mlsanity.com/paper/1705.02077/) (2017)

## Built on by (most cited first, 1 of 1)

- [Swiss4Arg: A Parallel Dataset for Multilingual Argument Mining across Swiss National Languages](https://mlsanity.com/paper/2610.17894/) (2026)

## Abstract (arXiv)

Argument mining is a subfield of natural language processing to identify and extract the argument components, like premises and conclusions, within a text and to recognize the relations between them. It reveals the logical structure of texts to be used in tasks like knowledge extraction. This paper aims at utilizing a cross-lingual approach to argument mining for low-resource languages, by constructing three training scenarios. We examine the models on English, as a high-resource language, and Persian, as a low-resource language. To this end, we evaluate the models based on the English Microtext corpus citepPeldszusStede2015, and its parallel Persian translation. The learning scenarios are as follow: (i) zero-shot transfer, where the model is trained solely with the English data, (ii) English-only training enhanced by synthetic examples generated by Large Language Models (LLMs), and (iii) a cross-lingual model that combines the original English data with manually translated Persian sentences. The zero-shot transfer model attains F1 scores of 50.2% on the English test set and 50.7% on the Persian test set. LLM-based augmentation model improves the performance up to 59.2% on English and 69.3% on Persian. The cross-lingual model, trained on both languages but evaluated solely on the Persian test set, surpasses the LLM-based variant, by achieving a F1 of 74.8%. Results indicate that a lightweight cross-lingual blend can outperform considerably the more resource-intensive augmentation pipelines, and it offers a practical pathway for the argument mining task to overcome data resource shortage on low-resource languages.