# TurkEmbed4Retrieval: Turkish Embedding Model for Retrieval Task

arXiv: https://arxiv.org/abs/2511.07595 · HTML: https://mlsanity.com/paper/2511.07595/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Nov 2025.

## Built on by (most cited first, 3 of 3)

- [Comparing Chunking and Embedding Strategies for Turkish RAG Systems](https://mlsanity.com/paper/2608.26192/) (2026)
- [Beyond Cosine Similarity: Taming Semantic Drift and Antonym Intrusion in a 15-Million Node Turkish Synonym Graph](https://mlsanity.com/paper/2601.13251/) (2026)
- [A Hybrid Protocol for Large-Scale Semantic Dataset Generation in Low-Resource Languages: The Turkish Semantic Relations Corpus](https://mlsanity.com/paper/2601.13253/) (2026)

## Abstract (arXiv)

In this work, we introduce TurkEmbed4Retrieval, a retrieval specialized variant of the TurkEmbed model originally designed for Natural Language Inference (NLI) and Semantic Textual Similarity (STS) tasks. By fine-tuning the base model on the MS MARCO TR dataset using advanced training techniques, including Matryoshka representation learning and a tailored multiple negatives ranking loss, we achieve SOTA performance for Turkish retrieval tasks. Extensive experiments demonstrate that our model outperforms Turkish colBERT by 19,26% on key retrieval metrics for the Scifact TR dataset, thereby establishing a new benchmark for Turkish information retrieval.