@inproceedings{meng-ilvovsky-2026-sifei,
    title = "Sifei at {S}em{E}val-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn {RAG}",
    author = "Meng, Sifei  and
      Ilvovsky, Dmitry",
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.32/",
    pages = "221--227",
    ISBN = "979-8-89176-414-9",
    abstract = "Multi-turn retrieval-augmented generation (RAG) is challenging due to evolving user intent, conversational noise, and strict context limits. We propose a training-free hybrid retrieval pipeline for SemEval-2026 Task 8 that combines dense and sparse retrieval with controlled query rewriting and cross-encoder reranking. Our system achieves 0.5453 nDCG@5 on the official test set of Task A, ranking 3rd out of 38 teams and outperforming the strongest baseline (0.4795). For Task C, we reuse the Task A retrieved documents in a lightweight generation pipeline based on the official prompt, achieving 0.5312 (harmonic mean of quality and faithfulness) and ranking 15th out of 29 teams. All retrieval components are open-source, while rewriting and generation use LLM APIs. Code and scripts are available on GitHub (https://github.com/mengsifei/MultiturnRAG)."
}