{"ID":2825240,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.11565","arxiv_id":"2601.11565","title":"Compass-Embedding v4: Robust Contrastive Learning for Multilingual E-commerce Embeddings","abstract":"As global e-commerce rapidly expands into emerging markets, the lack of high-quality semantic representations for low-resource languages has become a decisive bottleneck for retrieval, recommendation, and search systems. In this work, we present Compass-Embedding v4, a high-efficiency multilingual embedding framework specifically optimized for Southeast Asian (SEA) e-commerce scenarios, where data scarcity, noisy supervision, and strict production constraints jointly challenge representation learning. Compass-Embedding v4 addresses three core challenges. First, large-batch contrastive training under mixed task supervision introduces systematic false negatives that degrade semantic alignment. We propose Class-Aware Masking (CAM), a lightweight modification to the InfoNCE objective that suppresses invalid in-batch negatives and improves semantic discrimination without altering training efficiency. Second, low-resource SEA languages suffer from limited and uneven data coverage. We construct a diversified training corpus through context-grounded synthetic data generation, cross-lingual translation, and structured e-commerce data construction, enabling robust multilingual and domain-specific learning. Third, production deployment requires high-throughput inference while preserving embedding quality. We combine robustness-driven large-batch training with spherical model merging to mitigate catastrophic forgetting, and optimize inference via vLLM and FP8 quantization. Extensive evaluations across multilingual benchmarks and proprietary e-commerce tasks show that Compass-Embedding v4 achieves state-of-the-art performance on major SEA languages, significantly outperforming general-purpose embedding models in domain-specific retrieval and classification, while maintaining competitive performance on high-resource languages.","short_abstract":"As global e-commerce rapidly expands into emerging markets, the lack of high-quality semantic representations for low-resource languages has become a decisive bottleneck for retrieval, recommendation, and search systems. In this work, we present Compass-Embedding v4, a high-efficiency multilingual embedding framework s...","url_abs":"https://arxiv.org/abs/2601.11565","url_pdf":"https://arxiv.org/pdf/2601.11565v1","authors":"[\"Pakorn Ueareeworakul\",\"Shuman Liu\",\"Jinghao Feng\",\"Ling Hu\",\"Zhantang Shi\",\"Chengqi Sun\",\"Liang Yao\",\"Panyi Ouyang\",\"Haibo Zhang\",\"Anxiang Zeng\"]","published":"2025-12-25T13:41:53Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false}