5ting at SemEval-2026 Task 8: Strong End-to-End Multi-Turn RAG via LLM-Based Reranking and Faithfulness Control

About

We introduce 5ting, our system for the SemEval2026 Task 8 (MTRAGEval), which evaluates multi-turn Retrieval Augmented Generation (RAG) systems. Multi turn RAG involves context drift, under specification, and hallucination risk. Our system combines BGE-M3 dense retrieval with FAISS indexing, dual-query merged retrieval, and LLM based reranking, followed by role separated generation constrained to retrieved evidence. The retriever achieved nDCG@5 = 0.4719 in Task A, while the end to end system ranked in Task C with a harmonic score of 0.5597 and RL_F = 0.7692.

Thien-Qua-T-Nguyen, Chi Hoang, Nguyen Tran, Tri Le, Khanh Truong, Chinh Trong Nguyen · 2026

Related benchmarks

Task	Dataset	Result
Multi-turn RAG Generation	RAG Evaluation (dev)	RB_llm67	9
Information Retrieval	MT RAG (dev)	nDCG@543.9	5
Multi-turn RAG Generation	RAG Evaluation (test)	Combined Score0.5597	2
Information Retrieval	MT RAG (test)	nDCG@547.19	1