Performance of Multilingual Dense Retrieval Models on WebFAQ Benchmarks with Cross-Lingual Contrastive Learning

We present WebFAQ, a large-scale collection of open-domain question answering datasets derived from FAQ-style schema.org annotations. In total, the data collection consists of 96 million natural question-answer (QA) pairs across 75 languages, including 47 million (49\%) non-English samples. WebFAQ further serves as the foundation for 20 monolingual retrieval benchmarks with a total size of 11.2 million QA pairs (5.9 million non-English). These datasets are carefully curated through refined filtering and near-duplicate detection, yielding high-quality resources for training and evaluating multil

Research goal: How do state-of-the-art multilingual dense retrieval models compare to monolingual models on WebFAQ benchmarks when fine-tuned with cross-lingual contrastive learning, as evaluated by performance on zero-shot and few-shot retrieval tasks in low-resource languages?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.1/10.