DRU at WojoodNER 2024: ICL LLM for Arabic NER
Nancy Hamdan, Hadi Khaled Hamoud, Chadi Abou Chakra, Osama Rakan Al Mraikhat, Doha Albared, Fadi A. Zaraket · 2024
This paper details our submission to the Wo-joodNER Shared Task 2024, leveraging incontext learning with large language models for Arabic Named Entity Recognition.We utilized the Command R model, to perform fine-grained NER on the Wojood-Fine corpus.Our primary approach achieved an F1 score of 0.737 and a recall of 0.756.Post-processing the generated predictions to correct format inconsistencies resulted in an increased recall of 0.759, and a similar F1 score of 0.735.A multi-level prompting method and aggregation of outputs resulted in a lower F1 score of 0.637.Our results demonstrate the potential of ICL for Arabic NER while highlighting challenges related to LLM output consistency.