@inproceedings{revankar-etal-2026-slugrag,
    title = "{S}lug{RAG} at {S}em{E}val-2026 Task 8: Domain-Specific Fine-Tuning and Model Scaling for Multi-Turn {RAG} Retrieval",
    author = "Revankar, Pratibha  and
      Kim, Jihye  and
      Azirakhmet, Umit",
    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-1.135/",
    pages = "981--987",
    ISBN = "979-8-89176-414-9",
    abstract = "Multi-Turn Retrieval-Augmented Generation (MT-RAG) requires resolving context-dependent ambiguities across conversational turns. We present a systematic evaluation of dense retrieval optimization for the MTRAGEval benchmark (Task 8, Subtask A: Retrieval Only), investigating training-time strategies and inference-time query reformulation across four diverse English-language domains: CLAPNQ (legal/patent), FIQA (financial), GOVT (government documents), and CLOUD (cloud computing). Our experiments demonstrate that domain-specific fine-tuning yields the most substantial gains, with our best CLAPNQ model achieving Recall@10 of 0.6016 and nDCG@10 of 0.4981{---}representing 58.3{\textbackslash}{\%} and 66.0{\textbackslash}{\%} improvements over the pre-trained BGE baseline. Domain-specific models average 44.3{\textbackslash}{\%} improvement in Recall@10 and 47.8{\textbackslash}{\%} in nDCG@10 across all domains. Additionally, fine-tuning larger embedding models (BGE-large) achieves the best overall performance (nDCG@10: 0.5101, Recall@10: 0.6221), highlighting the complementary impact of model capacity and domain adaptation."
}