GHADAI at AraGenre 2026: Definition-Guided Classification of Arabic Text Genres via Bi-Encoder Retrieval and Large Language Model Reranking

Abstract

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 candidate definitions, and a large language model reranks the top candidates per sentence using cyclic option rotation to mitigate positional bias. On the hidden test set, the bi-encoder achieves a hierarchical macro-F1 of 0.4213, which increases to 0.5006 with Fanar-9B reranking and to 0.6050 with Qwen-32B reranking over the top 15 candidates using five rotations. The final pipeline ranked fourth on the official leaderboard. These results demonstrate the effectiveness of combining definition-based retrieval with LLM reranking for generalization to unseen Arabic text genres.