multi-turn-rag

#multi-turn-rag

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

arXiv cs.CL ↗ · 6d ago Cached

This paper presents 5ting, a system for multi-turn Retrieval-Augmented Generation (RAG) that combines BGE-M3 dense retrieval, FAISS indexing, LLM-based reranking, and evidence-constrained generation. The system achieves strong results on SemEval-2026 Task 8, with a retrieval nDCG@5 of 0.4719 and an end-to-end harmonic score of 0.5597.

0 favorites 0 likes

multi-turn-rag

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

Submit Feedback