Optimizing Domain-Specific RAG Architectures for Low-Resource Languages: An Ablation Study for Institutional Knowledge Assistants in Turkish Higher Education
SYMMETRY-BASEL, cilt.18, sa.10, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 18 Sayı: 10
- Basım Tarihi: 2026
- Doi Numarası: 10.3390/sym18101661
- Dergi Adı: SYMMETRY-BASEL
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, INSPEC, zbMATH, Academic Search Ultimate (EBSCO), Materials Science & Engineering Collection (ProQuest), Technology Collection (ProQuest)
- Kocaeli Üniversitesi Adresli: Evet
Özet
In higher education, hallucination-free information retrieval is critical for navigating complex institutional legislation. This study develops a highly accurate, production-ready Retrieval-Augmented Generation (RAG) architecture tailored to Turkish, a morphologically rich, low-resource language. We evaluate the pipeline using an expert-curated dataset of 846 canonical question-answer pairs derived from real-world student inquiries. Rigorous statistical testing reveals that while top embedding models achieve comparable, statistically indistinguishable retrieval accuracy, BAAI/bge-m3 demonstrates robust representational symmetry by maintaining identical document rankings across normalized distance metrics. Challenging common literature assumptions, our architectural ablation shows that dense retrieval alone is highly sufficient; hybrid (dense + sparse) fusion yields no meaningful accuracy gain when indices are constructed over equivalent text. At the generation layer, an efficiently sized 9-billion-parameter model matches or surpasses the response quality of much larger models-a ranking confirmed via repeated-run significance testing-while operating 3.9 times faster than a 32-billion-parameter counterpart and 2.5 times faster than an 8-billion-parameter alternative. Finally, we demonstrate that the latency benefits of INT8 Scalar Quantization are highly scale-dependent, accelerating retrieval in small-scale micro-benchmarks but increasing end-to-end latency at larger index scales. Ultimately, this study establishes that optimizing a production RAG system relies on selecting highly aligned, efficient components rather than maximizing architectural complexity or parameter count.