Comparing Chunking and Embedding Strategies for Turkish RAG Systems

Sicherheitsmeldung mit Schweregrad noch nicht bewertet. Technische Details im Tab „Originaltext“; empfohlene Schritte in der Checkliste.

Originaltext der Quelle (nicht übersetzt) – die deutsche Zusammenfassung findest du im Tab „Kurzfassung".

arXiv:2608.26192v1 Announce Type: cross Abstract: How documents are segmented into retrievable chunks and how those chunks are embedded strongly affect Retrieval-Augmented Generation (RAG) quality, yet neither has been systematically studied for morphologically rich languages such as Turkish. We compare Turkish document question answering across three chunking strategies (fixed-length, semantic, and layout-aware Docling), five embedding models, and two generator LLMs, over three documents with contrasting layouts. The fully crossed design yields 9,000 graded question-answer evaluations, each scored by an independent judge model, and component comparisons are tested by paired McNemar tests under Holm correction. Four findings follow. The chunking strategy determines how much the embedding choice matters: layout-aware chunking compresses the spread between the modern embedding models to about a point. The three leading embedding models are statistically indistinguishable, so language specialization yields no measurable retrieval advantage. The faster generator is not the more accurate one. And the preferred configuration depends on content type, since layout-aware chunking helps documents containing tables far more than prose. The best individual components therefore do not compose into the best complete configuration, which reaches 87.0%.

Vollständiger Originalartikel ↗

• Betroffenheit im eigenen Stack prüfen: Versionen/Komponenten abgleichen.
• Originalquelle / Hersteller-Advisory lesen: https://arxiv.org/abs/2608.26192
• Verfügbaren Patch oder Workaround einspielen und dokumentieren.