WathiqTeam at AraGenre 2026: Class-Balanced Hybrid Retrieval with Selective LLM Reranking

WathiqTeam at AraGenre 2026: Class-Balanced Hybrid Retrieval with Selective LLM Reranking

الملخص

We present WathiqTeam’s system for the Ara-Genre 2026 Shared Task on hierarchical Arabic genre classification. The task requires assigning each Arabic text both one of six broad genres and one of 74 fine-grained specific genres organised beneath them. This set...

We present WathiqTeam’s system for the Ara-Genre 2026 Shared Task on hierarchical Arabic genre classification. The task requires assigning each Arabic text both one of six broad genres and one of 74 fine-grained specific genres organised beneath them. This setting is particularly challenging because many specific genres overlap in topic and vocabulary, while the hierarchy is highly asymmetric: the six broad genres contain substantially different numbers of specific children. We address these challenges with a broad-first retrieval architecture. Multilingual E5 compares Arabic texts with English genre definitions, an Arabic sentence encoder retrieves generated Arabic prototypes, and BM25 preserves exact lexical and structural cues. At the broad level, class-balanced pooling prevents parents with larger prototype pools from receiving more votes. After hard hierarchical gating, Weighted Reciprocal Rank Fusion combines the three independent rankings for the remaining specific labels. Qwen3 reranks only uncertain top-two broad decisions and is constrained by internal ensemble support. The submitted system achieved 0.4559 Hierarchical Macro F1, with 0.6250 Broad Macro F1 and 0.2869 Specific Macro F1. Across adaptive official submissions, class balancing and level specific fusion produced most of the observed gain, while selective LLM reranking provided a small final improvement.

الباحثون

ملفات المنشور