RAGTurk: Best Practices for Retrieval Augmented Generation in Turkish
2nd Workshop on Natural Language Processing for Turkic Languages, SIGTURK 2026, Rabat, Morocco, 29 March 2026, pp.179-196, (Full Text)
- Publication Type: Conference Paper / Full Text
- Doi Number: 10.18653/v1/2026.sigturk-1.15
- City: Rabat
- Country: Morocco
- Page Numbers: pp.179-196
- Open Archive Collection: AVESIS Open Access Collection
- Middle East Technical University Affiliated: Yes
Abstract
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.