@inproceedings{czajka-etal-2026-amu,
    title = "{AMU} at {RAG}4{R}eports 2026 Task {B}: A Practical Multilingual {RAG} Pipeline for Citation-Grounded Reports",
    author = "Czajka, Maciej  and
      Jab{\l}o{\'n}ski, Piotr  and
      Czajka, Mateusz  and
      Pierzy{\'n}ski, Konrad  and
      Jassem, Krzysztof",
    editor = "Yang, Eugene  and
      Lawrie, Dawn  and
      MacAvaney, Sean  and
      Mayfield, James  and
      Soldaini, Luca  and
      Yates, Andrew",
    booktitle = "Proceedings of the 1st Workshop on Multilingual Report Generation via Retrieval Augmented Generation ({RAG}4{R}eports 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, CA, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.rag4reports-1.12/",
    pages = "89--93",
    ISBN = "979-8-89176-417-0",
    abstract = "This system paper presents AMU{'}s submission to RAG4Reports 2026 Task B: a practical multilingual retrieval-augmented generation pipeline for evidence-supported report generation. The system combines full-query retrieval, optional query rewriting, dense retrieval with Qdrant, cross-encoder reranking, diversity-aware context selection, and structured generation. The best submitted run uses BAAI/bge-m3 embeddings, BAAI/bge-reranker-v2-m3 reranking, and gpt-5.1 generation with medium reasoning effort, using a partial-coverage prompt strategy. On the official leaderboard, it achieved F1=0.4351, sentence{\_}support=0.8280, and nugget{\_}coverage=0.3403, indicating that the generated reports were well grounded but only partially comprehensive."
}