# RomanSetu: Efficiently unlocking multilingual capabilities of Large Language Models via Romanization

arXiv: https://arxiv.org/abs/2401.14280 · HTML: https://mlsanity.com/paper/2401.14280/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 56 references that are in the map.
- First posted on arXiv 25 Jan 2024.

## Builds on (most cited first, 30 of 36)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [The Flan Collection: Designing Data and Methods for Effective Instruction Tuning](https://mlsanity.com/paper/2301.13688/) (2023)
- [On the Cross-lingual Transferability of Monolingual Representations](https://mlsanity.com/paper/1910.11856/) (2019)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data](https://mlsanity.com/paper/1911.00359/) (2019)
- [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://mlsanity.com/paper/2306.04751/) (2023)
- [XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages](https://mlsanity.com/paper/2106.13822/) (2021)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca](https://mlsanity.com/paper/2304.08177/) (2023)
- [MEGA: Multilingual Evaluation of Generative AI](https://mlsanity.com/paper/2303.12528/) (2023)
- [Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.16039/) (2023)
- [IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages](https://mlsanity.com/paper/2305.16307/) (2023)
- [When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language Models](https://mlsanity.com/paper/2010.12858/) (2020)
- [SeaLLMs -- Large Language Models for Southeast Asia](https://mlsanity.com/paper/2312.00738/) (2023)
- [Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages](https://mlsanity.com/paper/2212.05409/) (2022)
- [WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models](https://mlsanity.com/paper/2112.06598/) (2021)
- [IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages](https://mlsanity.com/paper/2203.05437/) (2022)
- [IndicBART: A Pre-trained Model for Indic Natural Language Generation](https://mlsanity.com/paper/2109.02903/) (2021)

## Built on by (most cited first, 29 of 29)

- [Do Llamas Work in English? On the Latent Language of Multilingual Transformers](https://mlsanity.com/paper/2402.10588/) (2024)
- [The Emergence of Abstract Thought in Large Language Models Beyond Any Language](https://mlsanity.com/paper/2506.09890/) (2025)
- [Multilingual Large Language Models: A Systematic Survey](https://mlsanity.com/paper/2411.11072/) (2024)
- [RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs](https://mlsanity.com/paper/2502.07424/) (2025)
- [TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data](https://mlsanity.com/paper/2405.09913/) (2024)
- [TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking](https://mlsanity.com/paper/2502.11187/) (2025)
- [Facilitating large language model Russian adaptation with Learned Embedding Propagation](https://mlsanity.com/paper/2412.21140/) (2024)
- [LlamaTurk: Adapting Open-Source Generative Large Language Models for Low-Resource Language](https://mlsanity.com/paper/2405.07745/) (2024)
- [Lens: Rethinking Multilingual Enhancement for Large Language Models](https://mlsanity.com/paper/2410.04407/) (2024)
- [Prompting with Phonemes: Enhancing LLMs' Multilinguality for Non-Latin Script Languages](https://mlsanity.com/paper/2411.02398/) (2024)
- [Overcoming Vocabulary Constraints with Pixel-level Fallback](https://mlsanity.com/paper/2504.02122/) (2025)
- [Bhaasha, Bhasa, Zaban: A Survey for Low-Resourced Languages in South Asia -- Current Stage and Challenges](https://mlsanity.com/paper/2509.11570/) (2025)
- [Script Gap: Evaluating LLM Triage on Indian Languages in Native vs Romanized Scripts in a Real World Setting](https://mlsanity.com/paper/2512.10780/) (2025)
- [Can Small Language Models Learn, Unlearn, and Retain Noise Patterns?](https://mlsanity.com/paper/2407.00996/) (2024)
- [Happiness is Sharing a Vocabulary: A Study of Transliteration Methods](https://mlsanity.com/paper/2510.10827/) (2025)
- [Uncovering inequalities in new knowledge learning by large language models across different languages](https://mlsanity.com/paper/2503.04064/) (2025)
- [PrahokBART: A Pre-trained Sequence-to-Sequence Model for Khmer Natural Language Generation](https://mlsanity.com/paper/2512.13552/) (2025)
- [One Script Instead of Hundreds? On Pretraining Romanized Encoder Language Models](https://mlsanity.com/paper/2601.05776/) (2026)
- [Tracing Multilingual Knowledge Acquisition Dynamics in Domain Adaptation: A Case Study of English-Japanese Biomedical Adaptation](https://mlsanity.com/paper/2510.12115/) (2025)
- [Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration](https://mlsanity.com/paper/2601.02906/) (2026)
- [Script Sensitivity: Benchmarking Language Models on Unicode, Romanized and Mixed-Script Sinhala](https://mlsanity.com/paper/2601.14958/) (2026)
- [BhashaSetu: A Data-Centric Approach to Low-Resource Machine Translation](https://mlsanity.com/paper/2605.27050/) (2026)
- [The Latin Substrate: How Language Models Represent and Mediate Script Choice](https://mlsanity.com/paper/2605.31363/) (2026)
- [Indi-RomCoM: Code-Mixed Benchmark for Evaluating LLMs on Romanized Indic-English Instructions](https://mlsanity.com/paper/2606.30790/) (2026)
- [MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognition](https://mlsanity.com/paper/2607.24030/) (2026)
- [One Form to Transfer Them All: Pretraining Multilingual Language Models Beyond Native Orthography](https://mlsanity.com/paper/2608.25904/) (2026)
- [VakyArth: Evaluating Pragmatic Competence in LLMs across Indic Languages](https://mlsanity.com/paper/2609.01788/) (2026)
- [Why Pretraining Fails to Share Cross-Lingual Knowledge](https://mlsanity.com/paper/2609.19291/) (2026)
- [Recognized but Not Produced: A Generation Benchmark for Culturally Specific Kinship Terms](https://mlsanity.com/paper/2609.26942/) (2026)

## Abstract (arXiv)

This study addresses the challenge of extending Large Language Models (LLMs) to non-English languages that use non-Roman scripts. We propose an approach that utilizes the romanized form of text as an interface for LLMs, hypothesizing that its frequent informal use and shared tokens with English enhance cross-lingual alignment. Our approach involves the continual pretraining of an English LLM like Llama 2 on romanized text of non-English, non-Roman script languages, followed by instruction tuning on romanized data. The results indicate that romanized text not only reduces token fertility by 2x-4x but also matches or outperforms native script representation across various NLU, NLG, and MT tasks. Moreover, the embeddings computed on romanized text exhibit closer alignment with their English translations than those from the native script. Our approach presents a promising direction for leveraging the power of English LLMs in languages traditionally underrepresented in NLP. Our code is available on https://github.com/AI4Bharat/romansetu.