@inproceedings{abrishamchian-etal-2026-guir,
title = "{GUIR} at {S}em{E}val-2026 Task 8: Training-Free Multi-Query Fusion for Robust Conversational Retrieval",
author = "Abrishamchian, Pasha and
Frieder, Ophir and
Goharian, Nazli",
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-1.325/",
pages = "2583--2591",
ISBN = "979-8-89176-414-9",
abstract = "We describe our SemEval-2026 Task 8 Subtask A system, which focuses on evaluating and improving the retrieval aspect of multi-turn Retrieval-Augmented Generation (RAG) conversations. We implement a training-free fusion approach that combines three distinct query representations to retrieve documents independently. The results from these three views are pooled and reranked using a MonoT5 cross-encoder. Our findings demonstrate that this fusion approach consistently outperforms single-strategy baselines, revealing that optimal retrieval strategies vary significantly at the query level, and establishing multi-query fusion as a baseline for multi-turn RAG systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abrishamchian-etal-2026-guir">
<titleInfo>
<title>GUIR at SemEval-2026 Task 8: Training-Free Multi-Query Fusion for Robust Conversational Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pasha</namePart>
<namePart type="family">Abrishamchian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ophir</namePart>
<namePart type="family">Frieder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nazli</namePart>
<namePart type="family">Goharian</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>We describe our SemEval-2026 Task 8 Subtask A system, which focuses on evaluating and improving the retrieval aspect of multi-turn Retrieval-Augmented Generation (RAG) conversations. We implement a training-free fusion approach that combines three distinct query representations to retrieve documents independently. The results from these three views are pooled and reranked using a MonoT5 cross-encoder. Our findings demonstrate that this fusion approach consistently outperforms single-strategy baselines, revealing that optimal retrieval strategies vary significantly at the query level, and establishing multi-query fusion as a baseline for multi-turn RAG systems.</abstract>
<identifier type="citekey">abrishamchian-etal-2026-guir</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.325/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2583</start>
<end>2591</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GUIR at SemEval-2026 Task 8: Training-Free Multi-Query Fusion for Robust Conversational Retrieval
%A Abrishamchian, Pasha
%A Frieder, Ophir
%A Goharian, Nazli
%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 abrishamchian-etal-2026-guir
%X We describe our SemEval-2026 Task 8 Subtask A system, which focuses on evaluating and improving the retrieval aspect of multi-turn Retrieval-Augmented Generation (RAG) conversations. We implement a training-free fusion approach that combines three distinct query representations to retrieve documents independently. The results from these three views are pooled and reranked using a MonoT5 cross-encoder. Our findings demonstrate that this fusion approach consistently outperforms single-strategy baselines, revealing that optimal retrieval strategies vary significantly at the query level, and establishing multi-query fusion as a baseline for multi-turn RAG systems.
%U https://aclanthology.org/2026.semeval-1.325/
%P 2583-2591
Markdown (Informal)
[GUIR at SemEval-2026 Task 8: Training-Free Multi-Query Fusion for Robust Conversational Retrieval](https://aclanthology.org/2026.semeval-1.325/) (Abrishamchian et al., SemEval 2026)
ACL