# Information Loss in LLMs' Multilingual Translation: The Role of Training Data, Language Proximity, and Language Family

arXiv: https://arxiv.org/abs/2506.23340 · HTML: https://mlsanity.com/paper/2506.23340/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 6 references that are in the map.
- First posted on arXiv 29 Jun 2025.

## Builds on (most cited first, 5 of 5)

- [MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes](https://mlsanity.com/paper/2412.19260/) (2024)
- [Comparison of Diverse Decoding Methods from Conditional Language Models](https://mlsanity.com/paper/1906.06362/) (2019)
- [One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia](https://mlsanity.com/paper/2203.13357/) (2022)
- [Cross-Lingual Syntactic Transfer through Unsupervised Adaptation of Invertible Projections](https://mlsanity.com/paper/1906.02656/) (2019)
- [Could We Have Had Better Multilingual LLMs If English Was Not the Central Language?](https://mlsanity.com/paper/2402.13917/) (2024)

## Abstract (arXiv)

Large language models have achieved impressive progress in multilingual translation, yet they continue to face challenges with certain language pairs-particularly those with limited training data or significant linguistic divergence from English. This study systematically investigates how training data, language proximity, and language family affect information loss in multilingual translation. We evaluate two large language models, GPT-4 and Llama 2, by performing round-trip translations. Translation quality was assessed using BLEU scores and BERT similarity metrics. Our results reveal a robust interaction between training data size and language distance: while abundant training data can mitigate the effects of linguistic divergence, languages structurally closer to English consistently yield higher translation quality in low-resource conditions. Among various distance metrics, orthographic, phylogenetic, syntactic, and geographical distances emerge as strong predictors of translation performance. Language family also exerts an independent influence. These findings contribute to a deeper understanding of the linguistic constraints shaping multilingual translation in large language models, emphasizing that translation quality is shaped not only by data volume but also by structural and typological relationships between languages.