# Compass-v3: Scaling Domain-Specific LLMs for Multilingual E-Commerce in Southeast Asia

arXiv: https://arxiv.org/abs/2509.09121 · HTML: https://mlsanity.com/paper/2509.09121/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in MoE large language models, one of 12 directions in Mixture-of-experts.
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 11 Sep 2025.

## Placed in

- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

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

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [ST-MoE: Designing Stable and Transferable Sparse Expert Models](https://mlsanity.com/paper/2202.08906/) (2022)
- [Towards Generalist Biomedical AI](https://mlsanity.com/paper/2307.14334/) (2023)
- [Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy](https://mlsanity.com/paper/2507.01352/) (2025)
- [RegMix: Data Mixture as Regression for Language Model Pre-training](https://mlsanity.com/paper/2407.01492/) (2024)
- [HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages](https://mlsanity.com/paper/2505.11475/) (2025)
- [EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commerce](https://mlsanity.com/paper/2308.06966/) (2023)
- [eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data](https://mlsanity.com/paper/2402.08831/) (2024)
- [Maximize Your Data's Potential: Enhancing LLM Accuracy with Two-Phase Pretraining](https://mlsanity.com/paper/2412.15285/) (2024)
- [QuaDMix: Quality-Diversity Balanced Data Selection for Efficient LLM Pretraining](https://mlsanity.com/paper/2504.16511/) (2025)
- [A survey on fairness of large language models in e-commerce: progress, application, and challenge](https://mlsanity.com/paper/2405.13025/) (2024)
- [LLaMA-E: Empowering E-commerce Authoring with Object-Interleaved Instruction Following](https://mlsanity.com/paper/2308.04913/) (2023)
- [Optimal Transport-Based Token Weighting scheme for Enhanced Preference Optimization](https://mlsanity.com/paper/2505.18720/) (2025)
- [Compass-V2 Technical Report](https://mlsanity.com/paper/2504.15527/) (2025)

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

- [Each Prompt Matters: Scaling Reinforcement Learning Without Wasting Rollouts on Hundred-Billion-Scale MoE](https://mlsanity.com/paper/2512.07710/) (2025)
- [Valley3: Scaling Omni Foundation Models for E-commerce](https://mlsanity.com/paper/2605.01278/) (2026)
- [MUG-V 10B: High-efficiency Training Pipeline for Large Video Generation Models](https://mlsanity.com/paper/2510.17519/) (2025)

## Abstract (arXiv)

Large language models (LLMs) excel in general-domain applications, yet their performance often degrades in specialized tasks requiring domain-specific knowledge. E-commerce is particularly challenging, as its data are noisy, heterogeneous, multilingual, and highly dynamic. We present Compass-v3, a vertical-domain Mixture-of-Experts (MoE) model with 245B total parameters and 71B active per token, designed for Southeast Asian e-commerce. Compass-v3 adopts fewer but larger experts, combined with hardware-efficient optimizations-such as intra-node expert parallelism and a customized memcpy operator-to maximize GPU utilization. The model is trained on 12T tokens of curated multilingual corpora and large-scale synthetic e-commerce instructions using a mixed-training strategy. To enhance alignment, we propose Optimal-Transport Direct Preference Optimization (OTPO), which captures token-level distinctions and improves instruction adherence in commerce-specific scenarios. Extensive evaluations demonstrate that Compass-v3 delivers state-of-the-art e-commerce performance, surpassing DeepSeek-V3.1, GPT-4 series, and Qwen3-235B. Moreover, Compass-v3 demonstrates strong multilingual capability across low-resource Southeast Asian languages (Indonesian, Thai, Filipino, Vietnamese, Malay, Taglog) and Portuguese while sustaining competitive performance on general benchmarks. It has already been widely applied in Shopee's industrial-scale e-commerce platform and is gradually replacing OpenAI's traffic, now accounting for over 70% of total LLM usage, highlighting its dual strengths in specialized commerce expertise and broad linguistic competence.