An Exploration of Knowledge Editing for Arabic
This work addresses the underexamined behavior of knowledge editing in Arabic, providing benchmarks and multilingual training data to support future research in this domain-specific area.
The study tackled the problem of knowledge editing in Arabic, a morphologically rich language, by evaluating four methods on Arabic benchmarks and showing that instruction-tuned methods perform robustly, with joint Arabic-English training improving editability and transfer.
While Knowledge Editing (KE) has been widely explored in English, its behavior in morphologically rich languages like Arabic remains underexamined. In this work, we present the first study of Arabic KE. We evaluate four methods (ROME, MEMIT, ICE, and LTE) on Arabic translations of the ZsRE and Counterfact benchmarks, analyzing both multilingual and cross-lingual settings. Our experiments on Llama-2-7B-chat show that parameter-based methods struggle with cross-lingual generalization, while instruction-tuned methods perform more robustly. We extend Learning-To-Edit (LTE) to a multilingual setting and show that joint Arabic-English training improves both editability and transfer. We release Arabic KE benchmarks and multilingual training for LTE data to support future research.