RAGTurk: Best Practices for Retrieval Augmented Generation in Turkish


Creative Commons License

Köse S. K., Baytekin M. C., Aktaş B., Görür B. K., Munis E. A., Yılmaz D., ...Daha Fazla

2nd Workshop on Natural Language Processing for Turkic Languages, SIGTURK 2026, Rabat, Fas, 29 Mart 2026, ss.179-196, (Tam Metin Bildiri)

Özet

Retrieval-Augmented Generation (RAG) enhances LLM factuality, yet design guidance remains English-centric, limiting insights for morphologically rich languages like Turkish. We address this by constructing a comprehensive Turkish RAG dataset derived from Turkish Wikipedia and CulturaX, comprising question-answer pairs and relevant passage chunks. We benchmark seven stages of the RAG pipeline-from query transformation and reranking to answer refinement-without task-specific fine-tuning. Our results show that complex methods like HyDE maximize accuracy (85%) that is considerably higher than the baseline (78.70%). Also a Pareto-optimal configuration using Cross-encoder Reranking and Context Augmentation achieves comparable performance (84.60%) with much lower cost. We further demonstrate that over-stacking generative modules can degrade performance by distorting morphological cues, whereas simple query clarification with robust reranking offers an effective solution.