Arabic embeddings and rerankers Collection Retrieval models we evaluate for Arabic documents: multilingual and Arabic-specific embeddings, plus rerankers. Curated, not endorsed. • 16 items • Updated 23 days ago
Arabic LLMs we benchmark Collection Open-weight models AI Arm evaluates on Arabic document tasks: cited Q&A, long-document reasoning, report drafting. Curated, not endorsed. • 12 items • Updated 23 days ago