# OpenSeal: Good, Fast, and Cheap Construction of an Open-Source Southeast Asian LLM via Parallel Data

arXiv: https://arxiv.org/abs/2602.02266 · HTML: https://mlsanity.com/paper/2602.02266/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 22 of 22)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [XNLI: Evaluating Cross-lingual Sentence Representations](https://mlsanity.com/paper/1809.05053/) (2018)
- [MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies](https://mlsanity.com/paper/2404.06395/) (2024)
- [XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning](https://mlsanity.com/paper/2005.00333/) (2020)
- [Do Llamas Work in English? On the Latent Language of Multilingual Transformers](https://mlsanity.com/paper/2402.10588/) (2024)
- [PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification](https://mlsanity.com/paper/1908.11828/) (2019)
- [Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities](https://mlsanity.com/paper/2404.17790/) (2024)
- [SeaLLMs -- Large Language Models for Southeast Asia](https://mlsanity.com/paper/2312.00738/) (2023)
- [LLaMA Pro: Progressive LLaMA with Block Expansion](https://mlsanity.com/paper/2401.02415/) (2024)
- [ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora](https://mlsanity.com/paper/2012.15674/) (2020)
- [Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capability](https://mlsanity.com/paper/2305.10266/) (2023)
- [Persistent Pre-Training Poisoning of LLMs](https://mlsanity.com/paper/2410.13722/) (2024)
- [SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages](https://mlsanity.com/paper/2406.10118/) (2024)
- [MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs](https://mlsanity.com/paper/2104.08692/) (2021)
- [SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages](https://mlsanity.com/paper/2407.19672/) (2024)
- [Empowering Cross-lingual Abilities of Instruction-tuned Large Language Models by Translation-following demonstrations](https://mlsanity.com/paper/2308.14186/) (2023)
- [Breaking Language Barriers: Cross-Lingual Continual Pre-Training at Scale](https://mlsanity.com/paper/2407.02118/) (2024)
- [Just Go Parallel: Improving the Multilingual Capabilities of Large Language Models](https://mlsanity.com/paper/2506.13044/) (2025)

## Built on by (most cited first, 3 of 3)

- [Anthropogenic Regional Adaptation in Multimodal Vision-Language Model](https://mlsanity.com/paper/2604.11490/) (2026)
- [Equity with Efficiency: An Empirical Study of Tokenizers for Multilingual Large Language Models](https://mlsanity.com/paper/2606.15044/) (2026)
- [SEA-LION-v4.8: A Technical Report](https://mlsanity.com/paper/2609.18310/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have proven to be effective tools for a wide range of natural language processing (NLP) applications. Although many LLMs are multilingual, most remain English-centric and perform poorly on low-resource languages. Recently, several Southeast Asia-focused LLMs have been developed, but none are truly open source, as they do not publicly disclose their training data. Truly open-source models are important for transparency and for enabling a deeper and more precise understanding of LLM internals and development, including biases, generalization, and multilinguality. Motivated by recent advances demonstrating the effectiveness of parallel data in improving multilingual performance, we conduct controlled and comprehensive experiments to study the effectiveness of parallel data in continual pretraining of LLMs. Our findings show that using only parallel data is the most effective way to extend an LLM to new languages. Using just 34.7B tokens of parallel data and 180 hours on 8x NVIDIA H200 GPUs, we built OpenSeal, the first truly open Southeast Asian LLM that rivals the performance of existing models of similar size.