@inproceedings{raya-rios-etal-2026-iimas,
    title = "{IIMAS}-{RAG} at {S}em{E}val-2026 Task 8: Hybrid Sparse-Dense Retrieval and Answerability-Conditioned Generation for Multi-Turn {RAG}",
    author = "Raya-Rios, Vania  and
      Gomez-Adorno, Helena  and
      Hecht, Leon  and
      V{\'a}zquez-Osorio, Pedro  and
      Fabi{\'a}n-Sandoval, Erick  and
      V{\'a}zquez-Osorio, Jes{\'u}s  and
      Hern{\'a}ndez-Bustamante, Diego",
    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-1.345/",
    pages = "2744--2753",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper presents IIMAS-RAG, our system for SemEval-2026 Task 8 on evaluating multi-turn retrieval-augmented generation. Our approach combines LLM-based query rewriting, hybrid sparse-dense retrieval with SPLADE and Voyage-3-large fused via Reciprocal Rank Fusion, and answerability-conditioned generation with GPT-4.1. The system ranked 4th out of 38 teams in Subtask A (Retrieval) and 13th out of 29 teams in Subtask C (Full RAG). Our results show that query rewriting is the most impactful retrieval component, while generation remains challenging in low-context and partially answerable scenarios."
}