GHADAI at AraGenre 2026: Definition-Guided Classification of Arabic Text Genres via Bi-Encoder Retrieval and Large Language Model Reranking
We describe the GHADAI approach to the Ara-Genre 2026 shared task, which requires classifying Arabic text into broad and specific genre categories, including specific genres unseen during training. Our approach is a two-stage pipeline: a fine-tuned multilingual bi-encoder scores all 27,972 test sentences against the 74...