# SEA-LION-v4.8: A Technical Report

arXiv: https://arxiv.org/abs/2609.18310 · HTML: https://mlsanity.com/paper/2609.18310/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 14 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Builds on (most cited first, 11 of 11)

- [Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation](https://mlsanity.com/paper/2412.03304/) (2024)
- [Continual Pre-Training of Large Language Models: How to (re)warm your model?](https://mlsanity.com/paper/2308.04014/) (2023)
- [Instruction-tuned Language Models are Better Knowledge Learners](https://mlsanity.com/paper/2402.12847/) (2024)
- [Typhoon: Thai Large Language Models](https://mlsanity.com/paper/2312.13951/) (2023)
- [Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data](https://mlsanity.com/paper/2510.03264/) (2025)
- [SEA-HELM: Southeast Asian Holistic Evaluation of Language Models](https://mlsanity.com/paper/2502.14301/) (2025)
- [BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models](https://mlsanity.com/paper/2309.06085/) (2023)
- [How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining](https://mlsanity.com/paper/2511.18903/) (2025)
- [Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning](https://mlsanity.com/paper/2603.16127/) (2026)
- [OpenSeal: Good, Fast, and Cheap Construction of an Open-Source Southeast Asian LLM via Parallel Data](https://mlsanity.com/paper/2602.02266/) (2026)
- [BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models](https://mlsanity.com/paper/2602.18788/) (2026)

## Abstract (arXiv)

We introduce Nemotron-SEA-LION-v4.8, a family of Southeast Asian Languages In One Network (SEA-LION) models built upon NVIDIA Nemotron 3. The family includes 30B-A3B and 120B-A12B models, with both continued-pretrained base checkpoints and post-trained variants. We adapt the models using Southeast Asian, reasoning, code, and multilingual parallel data, followed by post-training with supervised fine-tuning and online on-policy distillation. On SEA-HELM, the 30B-A3B model improves the overall SEA score from 46.06 to 51.57, while the 120B-A12B model improves from 49.30 to 63.44. Across seven Southeast Asian languages, we observe broad capability gains with the 120B-A12B model showing broader and more consistent improvements across tasks.