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

The authors introduce 5ting, a system designed for the SemEval-2026 Task 8 (MTRAGEval) which evaluates multi-turn Retrieval Augmented Generation (RAG) systems. The system addresses challenges such as context drift, under specification, and hallucination risk by combining dense retrieval with LLM-based reranking and faithfulness control.

• The retriever utilizes BGE-M3 dense retrieval with FAISS indexing and dual-query merged retrieval.
• The end-to-end system employs LLM-based reranking followed by role-separated generation constrained to retrieved evidence.
• The retriever achieved an nDCG@5 score of 0.4719 in Task A.
• The end-to-end system ranked in Task C with a harmonic score of 0.5597 and an RL_F score of 0.7692.