@inproceedings{t-nguyen-etal-2026-5ting,
    title = "5ting at {S}em{E}val-2026 Task 8: Strong End-to-End Multi-Turn {RAG} via {LLM}-Based Reranking and Faithfulness Control",
    author = "T-Nguyen, Thien-Qua  and
      Hoang, Chi  and
      Tran, Nguyen  and
      Le, Tri  and
      Truong, Khanh  and
      Nguyen, Chinh",
    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-1.254/",
    pages = "2026--2033",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper presents a modular multi-turn Retrieval-Augmented Generation (RAG) system designed to mitigate hallucination, context drift, and underspecification. The pipeline combines dual-query merged retrieval and LLM-based reranking to deliver high-precision evidence, improving nDCG@5 by 17.7{\%}. To strictly control hallucination during generation, we introduce a role-separated prompting strategy. - This approach explicitly isolates the conversation history (used solely for intent and coreference resolution) from the retrieved passages (enforced as the exclusive source of factual grounding). - By preventing the language model from misinterpreting prior dialogue turns as factual evidence, the system ranked 3/29 in the SemEval-2026 Task 8 end-to-end evaluation. - Notably, our faithfulness-oriented design achieved a high ROUGE-L F1 score of 0.7692, outperforming larger baselines and demonstrating that explicit grounding constraints are highly effective at ensuring lexical faithfulness and reducing hallucinations."
}