@inproceedings{meng-ilvovsky-2026-sifei,
title = "Sifei at {S}em{E}val-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn {RAG}",
author = "Meng, Sifei and
Ilvovsky, Dmitry",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.32/",
pages = "221--227",
ISBN = "979-8-89176-414-9",
abstract = "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. Our system achieves 0.5453 nDCG@5 on the official test set of Task A, ranking 3rd out of 38 teams and outperforming the strongest baseline (0.4795). For Task C, we reuse the Task A retrieved documents in a lightweight generation pipeline based on the official prompt, achieving 0.5312 (harmonic mean of quality and faithfulness) and ranking 15th out of 29 teams. All retrieval components are open-source, while rewriting and generation use LLM APIs. Code and scripts are available on GitHub (https://github.com/mengsifei/MultiturnRAG)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meng-ilvovsky-2026-sifei">
<titleInfo>
<title>Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAG</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sifei</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitry</namePart>
<namePart type="family">Ilvovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>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. Our system achieves 0.5453 nDCG@5 on the official test set of Task A, ranking 3rd out of 38 teams and outperforming the strongest baseline (0.4795). For Task C, we reuse the Task A retrieved documents in a lightweight generation pipeline based on the official prompt, achieving 0.5312 (harmonic mean of quality and faithfulness) and ranking 15th out of 29 teams. All retrieval components are open-source, while rewriting and generation use LLM APIs. Code and scripts are available on GitHub (https://github.com/mengsifei/MultiturnRAG).</abstract>
<identifier type="citekey">meng-ilvovsky-2026-sifei</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.32/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>221</start>
<end>227</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAG
%A Meng, Sifei
%A Ilvovsky, Dmitry
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F meng-ilvovsky-2026-sifei
%X 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. Our system achieves 0.5453 nDCG@5 on the official test set of Task A, ranking 3rd out of 38 teams and outperforming the strongest baseline (0.4795). For Task C, we reuse the Task A retrieved documents in a lightweight generation pipeline based on the official prompt, achieving 0.5312 (harmonic mean of quality and faithfulness) and ranking 15th out of 29 teams. All retrieval components are open-source, while rewriting and generation use LLM APIs. Code and scripts are available on GitHub (https://github.com/mengsifei/MultiturnRAG).
%U https://aclanthology.org/2026.semeval-1.32/
%P 221-227
Markdown (Informal)
[Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAG](https://aclanthology.org/2026.semeval-1.32/) (Meng & Ilvovsky, SemEval 2026)
ACL