Year: 2026
Type: conference-paper
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) contextlevel 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.
Authors: Zehao Liu, Huizhi Liang
Institution: Newcastle University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166801138