Zehao Liu

NCL at SemEval-2026 Task 8: Deterministic Small-LLM RAG with Relation Classification

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 fall-back (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.