Open access
Aug 2026
Benchmarking retrieval augmented generation LLMs for Arabic noise robustness
This paper systematically investigated the capabilities of state-of-the-art multilingual LLMs with regard to two essential RAG abilities, noise robustness and negative rejection, and revealed that all six LLMs were negatively affected when the noise ratio in the external documents was increased.
Saleh Almohaimeed, Abdulrahman Alabduljabbar, Mousa Jari et al.
· Frontiers in Big Data · 1 citation