RexBERT: Context Specialized Bidirectional Encoders for E-commerce

TL;DR

RexBERT is a family of domain-specific BERT-style encoders optimized for e-commerce, trained on a large curated corpus, outperforming larger general models on relevant tasks.

Contribution

The paper introduces RexBERT, a specialized e-commerce encoder trained on a large domain-specific corpus with a new training recipe, achieving superior performance with fewer parameters.

Findings

RexBERT outperforms larger general-purpose encoders on e-commerce tasks.

A curated 350 billion token corpus enhances domain relevance.

A three-phase training recipe improves domain adaptation.

Abstract

Encoder-only transformers remain indispensable in retrieval, classification, and ranking systems where latency, stability, and cost are paramount. Most general purpose encoders, however, are trained on generic corpora with limited coverage of specialized domains. We introduce RexBERT, a family of BERT-style encoders designed specifically for e-commerce semantics. We make three contributions. First, we release Ecom-niverse, a 350 billion token corpus curated from diverse retail and shopping sources. We describe a modular pipeline that isolates and extracts e-commerce content from FineFineWeb and other open web resources, and characterize the resulting domain distribution. Second, we present a reproducible pretraining recipe building on ModernBERT's architectural advances. The recipe consists of three phases: general pre-training, context extension, and annealed domain specialization. Third, we train RexBERT models ranging from 17M to 400M parameters and evaluate them on token classification, semantic similarity, and general natural language understanding tasks using e-commerce datasets. Despite having 2-3x fewer parameters, RexBERT outperforms larger general-purpose encoders and matches or surpasses modern long-context models on domain-specific benchmarks. Our results demonstrate that high quality in-domain data combined with a principled training approach provides a stronger foundation for e-commerce applications than indiscriminate scaling alone.