# uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Reranking

arXiv: https://arxiv.org/abs/2606.11945 · HTML: https://mlsanity.com/paper/2606.11945/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 26 of 26)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering](https://mlsanity.com/paper/2307.16877/) (2023)
- [Open-Domain Question Answering Goes Conversational via Question Rewriting](https://mlsanity.com/paper/2010.04898/) (2020)
- [From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective](https://mlsanity.com/paper/2205.04733/) (2022)
- [TopiOCQA: Open-domain Conversational Question Answering with Topic Switching](https://mlsanity.com/paper/2110.00768/) (2021)
- [Question Rewriting for Conversational Question Answering](https://mlsanity.com/paper/2004.14652/) (2020)
- [Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search](https://mlsanity.com/paper/2303.06573/) (2023)
- [CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Search](https://mlsanity.com/paper/2406.05013/) (2024)
- [Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations](https://mlsanity.com/paper/2404.18812/) (2024)
- [RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented Dialogues](https://mlsanity.com/paper/2409.12558/) (2024)
- [A Unified Framework for Learned Sparse Retrieval](https://mlsanity.com/paper/2303.13416/) (2023)
- [TREC iKAT 2023: A Test Collection for Evaluating Conversational and Interactive Knowledge Assistants](https://mlsanity.com/paper/2405.02637/) (2024)
- [Scaling Sparse and Dense Retrieval in Decoder-Only LLMs](https://mlsanity.com/paper/2502.15526/) (2025)
- [UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations](https://mlsanity.com/paper/2507.07030/) (2025)
- [DiSCo: LLM Knowledge Distillation for Efficient Sparse Retrieval in Conversational Search](https://mlsanity.com/paper/2410.14609/) (2024)
- [Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval](https://mlsanity.com/paper/2504.05181/) (2025)
- [MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG Conversations](https://mlsanity.com/paper/2602.23184/) (2026)
- [Conversational Gold: Evaluating Personalized Conversational Search System using Gold Nuggets](https://mlsanity.com/paper/2503.09902/) (2025)
- [Generating Multi-Aspect Queries for Conversational Search](https://mlsanity.com/paper/2403.19302/) (2024)
- [IRLab@iKAT24: Learned Sparse Retrieval with Multi-aspect LLM Query Generation for Conversational Search](https://mlsanity.com/paper/2411.14739/) (2024)
- [ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answering](https://mlsanity.com/paper/2510.13312/) (2025)
- [Investigating LLM Variability in Personalized Conversational Information Retrieval](https://mlsanity.com/paper/2510.03795/) (2025)

## Abstract (arXiv)

This report describes our participation in SemEval-2026 Task 8 on multi-turn retrieval and question answering. The task evaluates conversational systems across four domains (finance, cloud documentation, government, Wikipedia), and includes unanswerable queries where the available collection does not contain sufficient evidence to produce a complete response. We propose a multi-turn retrieval-augmented generation pipeline that combines learned sparse retrieval with LLM-based reranking and generation. Using sparse retrieval as the primary retrieval method, we leverage its strong generalization across domains. In addition, we make use of the long-context capabilities of LLMs for conversational query rewriting, pointwise and listwise reranking, and generating the final response, each conditioned on the full conversational history. This multi-step design enables effective integration of conversational context throughout retrieval and generation, improving robustness across domains.