mlsanityData to 14 Oct 2026

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

arXiv 2606.28737 ↗First posted 27 Jun 2026cs.CL cs.AIcited by 0

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 8 of its 20 references that are in the map. First posted on arXiv 27 Jun 2026.

Builds on

8 of 20 references.

References · 8

  1. 2017Billion-scale similarity search with GPUscited by 2,497
  2. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  3. 2023RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!cited by 155
  4. 2020Question Rewriting for Conversational Question Answeringcited by 93
  5. 2024ChatQA: Surpassing GPT-4 on Conversational QA and RAGcited by 90
  6. 2025MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systemscited by 51
  7. 2023Exploiting Simulated User Feedback for Conversational Search: Ranking, Rewriting, and Beyondcited by 24
  8. 2026MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG Conversationscited by 9

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAG
  2. 2026AILS-NTUA at SemEval-2026 Task 8: Evaluating Multi-Turn RAG Conversations
  3. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  4. 2024XRAG: eXamining the Core -- Benchmarking Foundational Components in Advanced Retrieval-Augmented Generation
  5. 2025Leveraging LLM-Assisted Query Understanding for Live Retrieval-Augmented Generation
  6. 2025Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking
  7. 2024RAGGED: Towards Informed Design of Scalable and Stable RAG Systems
  8. 2024Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting