Asefa Mebrahtu Abera

GCCLA: Graph-Conditioned Cross-Lingual Adaptation of Large Language Models Under Extreme Data Scarcity (A Case Study in Tigrigna)

GCCLA is introduced, a graph-conditioned cross-lingual adaptation framework that integrates multilingual knowledge graphs into parameter-efficient LLM adaptation, conditioning a frozen multilingual LLM on structured semantic and typological relations to provide a strong inductive bias for data-efficient transfer.