# Comparing Approaches to Automatic Summarization in Less-Resourced Languages

arXiv: https://arxiv.org/abs/2512.24410 · HTML: https://mlsanity.com/paper/2512.24410/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 53 references that are in the map.
- First posted on arXiv 30 Dec 2025.

## Builds on (most cited first, 30 of 30)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [A Neural Attention Model for Abstractive Sentence Summarization](https://mlsanity.com/paper/1509.00685/) (2015)
- [XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages](https://mlsanity.com/paper/2106.13822/) (2021)
- [Neural Text Summarization: A Critical Evaluation](https://mlsanity.com/paper/1908.08960/) (2019)
- [Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier](https://mlsanity.com/paper/2412.04261/) (2024)
- [MLSUM: The Multilingual Summarization Corpus](https://mlsanity.com/paper/2004.14900/) (2020)
- [Multilingual is not enough: BERT for Finnish](https://mlsanity.com/paper/1912.07076/) (2019)
- [Self-training Improves Pre-training for Natural Language Understanding](https://mlsanity.com/paper/2010.02194/) (2020)
- [Fill in the BLANC: Human-free quality estimation of document summaries](https://mlsanity.com/paper/2002.09836/) (2020)
- [Self-Training with Weak Supervision](https://mlsanity.com/paper/2104.05514/) (2021)
- [BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation](https://mlsanity.com/paper/2210.07626/) (2022)
- [A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss](https://mlsanity.com/paper/1805.06266/) (2018)
- [How Does Quantization Affect Multilingual LLMs?](https://mlsanity.com/paper/2407.03211/) (2024)
- [Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training](https://mlsanity.com/paper/2109.05003/) (2021)
- [Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation](https://mlsanity.com/paper/2406.16678/) (2024)
- [M-Prometheus: A Suite of Open Multilingual LLM Judges](https://mlsanity.com/paper/2504.04953/) (2025)
- [Global Voices: Crossing Borders in Automatic News Summarization](https://mlsanity.com/paper/1910.00421/) (2019)
- [EstBERT: A Pretrained Language-Specific BERT for Estonian](https://mlsanity.com/paper/2011.04784/) (2020)
- [Multilingual Open Text Release 1: Public Domain News in 44 Languages](https://mlsanity.com/paper/2201.05609/) (2022)
- [A Hierarchical Structured Self-Attentive Model for Extractive Document Summarization (HSSAS)](https://mlsanity.com/paper/1805.07799/) (2018)
- [textttCOSMIC: Mutual Information for Task-Agnostic Summarization Evaluation](https://mlsanity.com/paper/2402.19457/) (2024)
- [LR-Sum: Summarization for Less-Resourced Languages](https://mlsanity.com/paper/2212.09674/) (2022)

## Abstract (arXiv)

Automatic text summarization has achieved high performance in high-resourced languages like English, but comparatively less attention has been given to summarization in less-resourced languages. This work compares a variety of different approaches to summarization from zero-shot prompting of LLMs large and small to fine-tuning smaller models like mT5 with and without three data augmentation approaches and multilingual transfer. We also explore an LLM translation pipeline approach, translating from the source language to English, summarizing and translating back. Evaluating with five different metrics, we find that there is variation across LLMs in their performance across similar parameter sizes, that our multilingual fine-tuned mT5 baseline outperforms most other approaches including zero-shot LLM performance for most metrics, and that LLM as judge may be less reliable on less-resourced languages.