Year: 2025
Type: conference-paper
Abstract: 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 show that parameter-based methods struggle with crosslingual 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.
Authors: Basel Mousi, Nadir Durrani, Fahim Dalvi
Institution: Hamad bin Khalifa University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W4416037691