{"slug": "5ting-at-semeval-2026-task-8-strong-end-to-end-multi-turn-rag-via-llm-based-and", "title": "5ting at SemEval-2026 Task 8: Strong End-to-End Multi-Turn RAG via LLM-Based Reranking and Faithfulness Control", "summary": "Researchers introduced 5ting, a system for the SemEval-2026 Task 8 (MTRAGEval) that combines BGE-M3 dense retrieval, FAISS indexing, dual-query merged retrieval, and LLM-based reranking with role-separated generation constrained to retrieved evidence. The retriever achieved nDCG@5 of 0.4719 in Task A, and the end-to-end system ranked in Task C with a harmonic score of 0.5597 and RL_F of 0.7692.", "body_md": "# Computer Science > Computation and Language\n\n[Submitted on 27 Jun 2026]\n\n# Title:5ting at SemEval-2026 Task 8: Strong End-to-End Multi-Turn RAG via LLM-Based Reranking and Faithfulness Control\n\n[View PDF](/pdf/2606.28737)\n\n[HTML (experimental)](https://arxiv.org/html/2606.28737v1)\n\nAbstract: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.\n\n## Submission history\n\nFrom: Thien-Qua T.Nguyen [[view email](/show-email/ac788e84/2606.28737)]\n\n**[v1]** Sat, 27 Jun 2026 05:13:49 UTC (326 KB)\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/5ting-at-semeval-2026-task-8-strong-end-to-end-multi-turn-rag-via-llm-based-and", "canonical_source": "https://arxiv.org/abs/2606.28737", "published_at": "2026-06-30 04:00:00+00:00", "updated_at": "2026-06-30 04:27:40.730740+00:00", "lang": "en", "topics": ["large-language-models", "natural-language-processing", "ai-research"], "entities": ["SemEval-2026", "MTRAGEval", "BGE-M3", "FAISS", "5ting", "Thien-Qua T.Nguyen"], "alternates": {"html": "https://wpnews.pro/news/5ting-at-semeval-2026-task-8-strong-end-to-end-multi-turn-rag-via-llm-based-and", "markdown": "https://wpnews.pro/news/5ting-at-semeval-2026-task-8-strong-end-to-end-multi-turn-rag-via-llm-based-and.md", "text": "https://wpnews.pro/news/5ting-at-semeval-2026-task-8-strong-end-to-end-multi-turn-rag-via-llm-based-and.txt", "jsonld": "https://wpnews.pro/news/5ting-at-semeval-2026-task-8-strong-end-to-end-multi-turn-rag-via-llm-based-and.jsonld"}}