Evaluation of Chunking Strategies for Effective Text Embedding in Low-Resource Language on Agricultural Documents
On the map: Retrieval-augmented generation → Multimodal RAG
Abstract (arXiv)
In this study, we compare the performance of four text chunking approaches: Recursive, Khmer-Aware, Sentence-Based, and LLM-Based within a Retrieval-Augmented Generation (RAG) framework applied to Khmer agricultural documents. The document chunks are encoded using the BGE-M3 multilingual embedding model and retrieved using the FAISS library. Performance is evaluated using four metrics: Average Retrieval Score (L2 distance), Answer Relevance, Khmer Coverage, and Khmer Intersection over Union, all measured against ground-truth question-answer pairs. For evaluation, we perform 5-fold cross-validation over 18 question-answer pairs. We observe the best performance for the character-based Recursive chunking method with a chunk size of 300 characters, achieving the lowest L2 distance (0.4295 +- 0.0461), highest Answer Relevance (0.8663 +- 0.0199), and highest Khmer IoU (0.6441 +- 0.0347). A paired t-test shows a statistically significant improvement over the Sentence-Based chunking method in L2 distance (p = 0.0121). These results highlight the importance of segmentation granularity and structural preservation for optimizing dense retrieval in morphologically complex, low-resource languages such as Khmer.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation. Builds on 16 of its 19 references that are in the map. First posted on arXiv 21 May 2026.
Builds on
16 of 19 references.
Closest ancestors · 2
Same direction, newest first
- 2025Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation28 Apr
- 2024Is Semantic Chunking Worth the Computational Cost?16 Oct
Other references · 14
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
- 2017Billion-scale similarity search with GPUscited by 2,497
- 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
- 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
- 2018Text Segmentation as a Supervised Learning Taskcited by 76
- 2024Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Modelscited by 73
- 2018VnCoreNLP: A Vietnamese Natural Language Processing Toolkitcited by 51
- 2022Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languagescited by 47
- 2025SEA-HELM: Southeast Asian Holistic Evaluation of Language Modelscited by 19
- 2023BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Modelscited by 18
2 more
- 2015Text Segmentation based on Semantic Word Embeddingscited by 11
- 2025The Attribution Crisis in LLM Search Resultscited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026A Comparative Study of Language Models for Khmer Retrieval-Augmented Question Answering
- 2026Comparing Chunking and Embedding Strategies for Turkish RAG Systems
- 2026Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts
- 2025SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG
- 2026Evaluating Chunking Strategies For Retrieval-Augmented Generation in Oil and Gas Enterprise Documents
- 2025MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System
- 2025A New HOPE: Domain-agnostic Automatic Evaluation of Text Chunking
- 2026A Systematic Analysis of Chunking Strategies for Reliable Question Answering