Noor Abdul Khaleq Zghair

Semantic-Driven Context Pruning for Arabic RAG: Quality-Preserving Compression Under Token Inflation

Retrieval-Augmented Generation (RAG) for Modern Standard Arabic (MSA) is costly because Arabic needs more tokens than English for the same content, which enlarges the context the generator must hold. We evaluate sentence-level cross-encoder context pruning for Arabic RAG, adapting a DSLR-style split-score-reassemble pi...