Comparing Approaches to Automatic Summarization in Less-Resourced Languages
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909978841841664 |
|---|---|
| author | Palen-Michel, Chester Lignos, Constantine |
| author_facet | Palen-Michel, Chester Lignos, Constantine |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_24410 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Comparing Approaches to Automatic Summarization in Less-Resourced Languages Palen-Michel, Chester Lignos, Constantine Computation and Language Artificial Intelligence 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. |
| title | Comparing Approaches to Automatic Summarization in Less-Resourced Languages |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2512.24410 |