mlsanityData to 7 Oct 2026

Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAG

arXiv 2606.28352 ↗First posted 5 Jun 2026cs.IR cs.CLcited by 0

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

Multi-turn retrieval-augmented generation (RAG) is challenging due to evolving user intent, conversational noise, and strict context limits. We propose a training-free hybrid retrieval pipeline for SemEval-2026 Task 8 that combines dense and sparse retrieval with controlled query rewriting and cross-encoder reranking. On the official test set of Task A, our system achieves 0.5453 nDCG@5, ranking third among 38 teams and outperforming the strongest baseline score of 0.4795. For Task C, we reuse the documents retrieved for Task A and apply a lightweight generation pipeline guided by the official prompt, achieving 0.5312 as the harmonic mean of relevance and faithfulness and ranking 15th among 29 teams. All retrieval components are open-source, while query rewriting and answer generation rely on LLM APIs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 7 of its 11 references that are in the map. First posted on arXiv 5 Jun 2026.

Builds on

7 of 11 references.

References · 7

  1. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
  2. 2024SPLADE-v3: New baselines for SPLADEcited by 69
  3. 2025MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systemscited by 50
  4. 2024HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applicationscited by 22
  5. 2024Multi-Reranker: Maximizing performance of retrieval-augmented generation in the FinanceRAG challengecited by 10
  6. 2026MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG Conversationscited by 8
  7. 2025Jasper-Token-Compression-600M Technical Reportcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Better Together: Complementary Query Rewriting Under a Strong RAG Baseline
  2. 20265ting at SemEval-2026 Task 8: Strong End-to-End Multi-Turn RAG via LLM-Based Reranking and Faithfulness Control
  3. 2024DMQR-RAG: Diverse Multi-Query Rewriting for RAG
  4. 2025PreQRAG -- Classify and Rewrite for Enhanced RAG
  5. 2025LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers
  6. 2026AILS-NTUA at SemEval-2026 Task 8: Evaluating Multi-Turn RAG Conversations
  7. 2026Beyond the Reranker: Do RAG Retrieval Enhancements Help Once a Strong Reranker Is Present?
  8. 2024CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversity