@inproceedings{nacar-etal-2026-gate,
    title = "{GATE}-Reranker: A Strong {A}rabic Cross-Encoder for Document Reranking",
    author = "Nacar, Omer  and
      Elshehy, Omar  and
      Zaytoon, Mohamed  and
      Al Jallad, Khloud",
    editor = "Al-Khalifa, Hend  and
      El-Haj, Mo  and
      Ezzini, Saad",
    booktitle = "The 7th Workshop on Open-Source {A}rabic Corpora and Processing Tools ({OSACT}7) with 5 Shared Tasks",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/test-year-match/2026.osact-1.5/",
    doi = "10.63317/2y297wwcf77y",
    pages = "40--48",
    abstract = "Arabic information retrieval increasingly relies on multi-stage pipelines in which a fast first-stage retriever produces candidate passages and a neural reranker refines relevance. While transformer cross-encoders deliver strong effectiveness through joint query{--}passage encoding, multilingual rerankers achieve competitive performance on Arabic benchmarks. However, systematic analysis of calibration, robustness, and deployment behavior in Arabic-specific settings remains limited. We present \textbf{GATE-Reranker}, a compact Arabic cross-encoder initialized from an Arabic semantic embedding backbone and fine-tuned on large-scale mMARCO-style Arabic triplets. The model scores each query{--}passage pair via full self-attention and a lightweight regression head, enabling plug-and-play second-stage reranking for Arabic search and RAG systems. We evaluate on three Arabic benchmarks covering binary relevance discrimination, controlled multi-negative reranking, and large-scale mMARCO evaluation. While remaining competitive with strong multilingual rerankers in ranking effectiveness, GATE-Reranker demonstrates significantly improved calibration and discriminative behavior. These properties translate into more reliable downstream performance in retrieval and RAG pipelines, while maintaining low GPU memory and latency on a Tesla T4."
}