arXiv AI August 28, 2026 By Mustafa Serta\c{c} T\"urkel, Fatma Nur Korkmaz, Ahmet Tu\u{g}rul Bayrak

Comparing Chunking and Embedding Strategies for Turkish RAG Systems

The study investigates how document segmentation (chunking) and embedding choices influence Retrieval-Augmented Generation (RAG) performance for Turkish, a morphologically rich language. Using a fully crossed experimental design, the authors compare three chunking strategies (fixed-length, semantic, and layout-aware Docling), five embedding models, and two large language model generators across three documents with different layouts, generating 9,000 graded question-answer evaluations. Key findings include that layout-aware chunking reduces the impact of embedding choice, the top embedding models perform similarly, faster generators are not more accurate, and the optimal configuration varies with content type, achieving a best overall accuracy of 87.0%.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 3

Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts

arXiv:2607. 01852v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems use the question-answering capabilities of Large Language Models (LLMs) to access information outside their parameters.

By Valentin J. J. Kreileder, Johannes Reisinger, Andreas Fischer

llms rag

Hugging Face Trending Papers

Jul 2

Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts

Retrieval-Augmented Generation (RAG) systems use the question-answering capabilities of Large Language Models (LLMs) to access information outside their parameters. We evaluate if cluster-based semantic chunking improves retrieval and answer quality compared to fixed-size and recursive chunking evaluating on long, structured academic theses using the Retrieval Augmented Generation Assessment (RAGAs) framework.

llms rag

arXiv AI

Jun 30

A Systems-Level Analysis of Sensitivity, Robustness, and Stability in Retrieval-Augmented Generation

arXiv:2606. 28337v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are often evaluated using final answer accuracy, even though their failures can originate from preprocessing, retrieval, context packing, or generation.

By Bharath Simha Reddy Muthyam

rag

arXiv Computation and Language

Sep 14

EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Development

The paper introduces EAR, an Entity‑Aware Partitioning approach that improves retrieval‑augmented generation for multiple‑choice question answering by extracting normalized surface anchors from questions, answers, and the corpus. EAR retrieves local windows around matching anchors and can attach a larger parent passage via an extractive summary, reducing retrieved words by 37.5‑40.2% compared to fixed‑size chunks. Experiments on a cleaned MMLU‑style subset with Mistral, Gemma, and DeepSeek show modest accuracy changes, none statistically significant, highlighting EAR’s methodological contribution of compact, inspectable retrieval units.

By Cenab Batu Bora, Oylum Alatl{\i}, Sebnem Bora, Oguz Dikenelli

llms rag nlp benchmarks

Hugging Face Trending Papers

Sep 23

Evaluating Open-Weight LLMs for Turkish Domain Documents Under Retrieval and Hardware Constraints

Most Turkish-capable large language models (LLMs) are evaluated using general-purpose benchmarks rather than long, structurally complex domain documents. This paper evaluates five open-weight 7B-8B mo...

llms nlp benchmarks

arXiv AI

Jul 29

The Effect of Text Chunk Size on Retrieval-Augmented Generation Performance

arXiv:2607. 24767v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems have emerged as a powerful process for allowing large language models (LLMs) to retrieve relevant information to use as source material during text generation.

By German Garrido-Lestache Belinchon, Hugo Garrido-Lestache Belinchon

llms rag computer-vision

One email a morning, machine-written

Related stories

Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts

Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts

A Systems-Level Analysis of Sensitivity, Robustness, and Stability in Retrieval-Augmented Generation

EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Development

Evaluating Open-Weight LLMs for Turkish Domain Documents Under Retrieval and Hardware Constraints

The Effect of Text Chunk Size on Retrieval-Augmented Generation Performance