CLSep 11, 2025

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

arXiv:2509.09121v13 citationsh-index: 1
Originality Incremental advance
AI Analysis

This addresses the challenge of adapting LLMs to noisy, multilingual e-commerce data for platforms like Shopee in Southeast Asia, representing a domain-specific advancement.

The paper tackles the problem of LLM performance degradation in specialized e-commerce tasks by introducing Compass-v3, a 245B parameter Mixture-of-Experts model optimized for Southeast Asian e-commerce, which achieves state-of-the-art performance surpassing models like GPT-4 and has replaced over 70% of LLM usage in Shopee's platform.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes