@inproceedings{zhang-etal-2026-uircis,
    title = "uircis at {S}em{E}val-2026 Task 8: A Unified Lightweight Pipeline for Multi-Turn {RAG} Evaluation",
    author = "Zhang, Jiaqi  and
      Duan, Wenbin  and
      Zhang, Yingqi  and
      Li, Yan  and
      Li, Binyang",
    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-1.394/",
    pages = "3143--3148",
    ISBN = "979-8-89176-414-9",
    abstract = "We submit a system description paper for SemEval-2026 Task 8 (MTRAGEval), covering both Subtask A (retrieval) and Subtask B (generation). Our approach is a lightweight, fully reproducible multi-turn RAG pipeline using open-weight models: Qwen2.5-7B-Instruct for query rewriting and grounded answer generation, BGE-M3 for dense retrieval, and BGE-Reranker-v2-M3 for cross-encoder reranking. We report official test performance, conduct ablation experiments to quantify the impact of rewriting and reranking across domains, and provide error analysis using the organizers' analytics and answerability classes, highlighting key failure modes in multi-turn retrieval specificity and grounded generation."
}