mlsanityData to 7 Oct 2026

RAGTurk: Best Practices for Retrieval Augmented Generation in Turkish

arXiv 2602.03652 ↗First posted 3 Feb 2026cs.CL cs.AI cs.IRcited by 1

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 29 of its 52 references that are in the map. First posted on arXiv 3 Feb 2026.

Builds on

29 of 52 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets3 Nov
  2. 2024AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation Pipeline28 Oct
  3. 2024Evaluation of Retrieval-Augmented Generation: A Survey13 May
  4. 2024Retrieval-Augmented Generation for AI-Generated Content: A Survey29 Feb

Other references · 25

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  7. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  8. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,346
  9. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  10. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  11. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  12. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,258
13 more
  1. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  2. 2024The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scalecited by 1,104
  3. 2019Passage Re-ranking with BERTcited by 629
  4. 2019CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Datacited by 544
  5. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  6. 2024Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Researchcited by 475
  7. 2020Generation-Augmented Retrieval for Open-domain Question Answeringcited by 186
  8. 2023CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languagescited by 172
  9. 2025Evaluating the Quality of Benchmark Datasets for Low-Resource Languages: A Case Study on Turkishcited by 12
  10. 2022Resources for Turkish Natural Language Processing: A critical surveycited by 6
  11. 2025Passage Segmentation of Documents for Extractive Question Answeringcited by 6
  12. 2025Query Expansion in the Age of Pre-trained and Large Language Models: A Comprehensive Surveycited by 5
  13. 2025Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applicationscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Developmentcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions
  2. 2024CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversity
  3. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
  4. 2025Optimizing RAG Pipelines for Arabic: A Systematic Analysis of Core Components
  5. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  6. 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
  7. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Models
  8. 2025The Cross-Lingual Cost: Retrieval Biases in RAG over Arabic-English Corpora