5ting at SemEval-2026 Task 8: Strong End-to-End Multi-Turn RAG via LLM-Based Reranking and Faithfulness Control
Year: 2026
Type: conference-paper
Abstract: We introduce 5ting, our system for the SemEval-2026 Task 8 (MTRAGEval), which evaluates multi-turn Retrieval-Augmented Generation (RAG) systems.Multi-turn RAG involves context drift, underspecification, and hallucination risk.Our system combines BGE-M3 dense retrieval with FAISS indexing, dualquery 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.
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166847604