Brief

Researchers evaluated four text chunking strategies for a Retrieval-Augmented Generation (RAG) framework using Khmer agricultural documents. The study found that a character-based Recursive chunking method, with a chunk size of 300 characters, performed best. This approach achieved the lowest L2 distance and highest Answer Relevance and Khmer Intersection over Union scores, demonstrating significant improvement over sentence-based methods. AI

A new study explores the effectiveness of Retrieval-Augmented Generation (RAG) for the Khmer language, a low-resource, non-Latin script. Researchers benchmarked three embedding models for dense retrieval, finding BGE-M3 to be the top performer. They then evaluated five generator models, noting that no single model excelled across all metrics, with Qwen3.5-9B leading in faithfulness and context relevance, Qwen3-8B in factual correctness, and SeaLLMs-v3-7B-Chat in answer relevance and correctness. AI