pith. sign in

arxiv: 2502.12982 · v1 · pith:IWVM27HEnew · submitted 2025-02-18 · 💻 cs.CL · cs.AI· cs.LG

Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs

Longxu Dou , Qian Liu , Fan Zhou , Changyu Chen , Zili Wang , Ziqi Jin , Zichen Liu , Tongyao Zhu
show 33 more authors
Cunxiao Du Penghui Yang Haonan Wang Jiaheng Liu Yongchi Zhao Xiachong Feng Xin Mao Man Tsung Yeung Kunat Pipatanakul Fajri Koto Min Si Thu Hynek Kydl\'i\v{c}ek Zeyi Liu Qunshu Lin Sittipong Sripaisarnmongkol Kridtaphad Sae-Khow Nirattisai Thongchim Taechawat Konkaew Narong Borijindargoon Anh Dao Matichon Maneegard Phakphum Artkaew Zheng-Xin Yong Quan Nguyen Wannaphong Phatthiyaphaibun Hoang H. Tran Mike Zhang Shiqi Chen Tianyu Pang Chao Du Xinyi Wan Wei Lu Min Lin
This is my paper
classification 💻 cs.CL cs.AIcs.LG
keywords sailor2languagesmodelmultilingualcookbookinclusivelanguagellms
0
0 comments X
read the original abstract

Sailor2 is a family of cutting-edge multilingual language models for South-East Asian (SEA) languages, available in 1B, 8B, and 20B sizes to suit diverse applications. Building on Qwen2.5, Sailor2 undergoes continuous pre-training on 500B tokens (400B SEA-specific and 100B replay tokens) to support 13 SEA languages while retaining proficiency in Chinese and English. Sailor2-20B model achieves a 50-50 win rate against GPT-4o across SEA languages. We also deliver a comprehensive cookbook on how to develop the multilingual model in an efficient manner, including five key aspects: data curation, pre-training, post-training, model customization and evaluation. We hope that Sailor2 model (Apache 2.0 license) will drive language development in the SEA region, and Sailor2 cookbook will inspire researchers to build more inclusive LLMs for other under-served languages.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE

    cs.CL 2026-05 unverdicted novelty 7.0

    PARAMΔ upcycles dense models to MoE for per-language experts and grafts post-training deltas to enable data-efficient language expansion while preserving original capabilities.

  2. XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity

    cs.CL 2026-05 unverdicted novelty 7.0

    XL-SafetyBench is a new cross-cultural benchmark showing frontier LLMs decouple jailbreak robustness from cultural sensitivity while local models trade off attack success against neutral-safe rates in a near-linear pa...

  3. A Comparative Study of Language Models for Khmer Retrieval-Augmented Question Answering

    cs.CL 2026-05 unverdicted novelty 3.0

    Comparative benchmark of three embedding models and five generators for Khmer RAG shows BGE-M3 best for retrieval and no single generator leading on all RAGAS metrics.

  4. Phoenix-VL 1.5 Medium Technical Report

    cs.CL 2026-05 unverdicted novelty 3.0

    Phoenix-VL 1.5 Medium is a 123B-parameter natively multimodal model that reaches state-of-the-art results on Singapore multimodal, legal, and policy benchmarks after localized training on 1T+ tokens while staying comp...