@inproceedings{liu-liang-2026-ncl,
    title = "{NCL} at {S}em{E}val-2026 Task 8: Deterministic Small-{LLM} {RAG} with Relation Classification",
    author = "Liu, Zehao  and
      Liang, Huizhi",
    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-1.191/",
    pages = "1477--1481",
    ISBN = "979-8-89176-414-9",
    abstract = "We present NCL{'}s system for SemEval-2026 Task 8B, the generation track for multi-turn retrieval-augmented dialogues. Our submission follows a compact and reproducible RAG pipeline: (1) global and local question rewriting with LLM-based multi-turn relation control, (2) passage reranking with BGE-M3, (3) context-level answerability filtering with strict binary LLM judgments ({``}yes''/{``}no''), and (4) deterministic inference with a small-LLM (Qwen2.5-1.5B-Instruct) plus post-generation quality fallback (cleaning, bad-answer gate, one stricter retry, then an IDK fallback).On the official test set, our system achieved a harmonic mean score of 0.5973 (RB{\$}{\{}agg{\}}{\$} 0.4993, RL{\$}F{\$} 0.7235, RB{\$}{\{}llm{\}}{\$} 0.6105), ranking 19th out of 26 teams on the leaderboard."
}