@inproceedings{celik-etal-2026-polito,
title = "Polito Team at {S}em{E}val-2026 Task 8: Scaling Multi-Turn {RAG}: High-Performance Parallelized Pipeline for the {MTRAG} Benchmark",
author = {{\c{C}}elik, Murat and
Din{\c{c}}er, Nejla and
Ersoy, Can and
Toprak, Mert and
{\"U}nal, Bar{\i}{\c{s}} and
Coppola, Riccardo and
Giobergia, Flavio},
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-1.309/",
pages = "2447--2455",
ISBN = "979-8-89176-414-9",
abstract = "Recently, Retrieval-Augmented Generation (RAG) has become a significant task in Large Language Models (LLMs). In multi-turn RAG, a good system must overcome the challenges of maintaining context as the dialogue turns progress and manage the issue of generating answers based on conversation history. In this work, we address the MTRAGEval task 8 at SemEval-2026, by presenting a high-performance, parallelised Multi-Turn RAG pipeline designed to address three subtasks: Retrieval (Subtask A), Generation (Subtask B), and End-to-End RAG (Subtask C). Our methodology utilises a Streamlit framework that allows users to embed diverse corpora with varying vector spaces and embedding models, facilitating configuration for each task based on its nature. Some key experiments focus on the performance of different vector databases and embedding models, the necessity of LLM-based query rewriting (QR) for non-standalone questions, the use of different rerankers, and the scale and performance of the selected LLM for answer generation. We conclude that a configuration utilising query rewriting along with reranking delivers the best results. The code is available on GitHub https://github.com/merttoprak1/MTRAGEval-Evaluating-Multi-Turn-RAG-Conversations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="celik-etal-2026-polito">
<titleInfo>
<title>Polito Team at SemEval-2026 Task 8: Scaling Multi-Turn RAG: High-Performance Parallelized Pipeline for the MTRAG Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Murat</namePart>
<namePart type="family">Çelik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nejla</namePart>
<namePart type="family">Dinçer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Can</namePart>
<namePart type="family">Ersoy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mert</namePart>
<namePart type="family">Toprak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barış</namePart>
<namePart type="family">Ünal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riccardo</namePart>
<namePart type="family">Coppola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flavio</namePart>
<namePart type="family">Giobergia</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>Recently, Retrieval-Augmented Generation (RAG) has become a significant task in Large Language Models (LLMs). In multi-turn RAG, a good system must overcome the challenges of maintaining context as the dialogue turns progress and manage the issue of generating answers based on conversation history. In this work, we address the MTRAGEval task 8 at SemEval-2026, by presenting a high-performance, parallelised Multi-Turn RAG pipeline designed to address three subtasks: Retrieval (Subtask A), Generation (Subtask B), and End-to-End RAG (Subtask C). Our methodology utilises a Streamlit framework that allows users to embed diverse corpora with varying vector spaces and embedding models, facilitating configuration for each task based on its nature. Some key experiments focus on the performance of different vector databases and embedding models, the necessity of LLM-based query rewriting (QR) for non-standalone questions, the use of different rerankers, and the scale and performance of the selected LLM for answer generation. We conclude that a configuration utilising query rewriting along with reranking delivers the best results. The code is available on GitHub https://github.com/merttoprak1/MTRAGEval-Evaluating-Multi-Turn-RAG-Conversations.</abstract>
<identifier type="citekey">celik-etal-2026-polito</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.309/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2447</start>
<end>2455</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Polito Team at SemEval-2026 Task 8: Scaling Multi-Turn RAG: High-Performance Parallelized Pipeline for the MTRAG Benchmark
%A Çelik, Murat
%A Dinçer, Nejla
%A Ersoy, Can
%A Toprak, Mert
%A Ünal, Barış
%A Coppola, Riccardo
%A Giobergia, Flavio
%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 celik-etal-2026-polito
%X Recently, Retrieval-Augmented Generation (RAG) has become a significant task in Large Language Models (LLMs). In multi-turn RAG, a good system must overcome the challenges of maintaining context as the dialogue turns progress and manage the issue of generating answers based on conversation history. In this work, we address the MTRAGEval task 8 at SemEval-2026, by presenting a high-performance, parallelised Multi-Turn RAG pipeline designed to address three subtasks: Retrieval (Subtask A), Generation (Subtask B), and End-to-End RAG (Subtask C). Our methodology utilises a Streamlit framework that allows users to embed diverse corpora with varying vector spaces and embedding models, facilitating configuration for each task based on its nature. Some key experiments focus on the performance of different vector databases and embedding models, the necessity of LLM-based query rewriting (QR) for non-standalone questions, the use of different rerankers, and the scale and performance of the selected LLM for answer generation. We conclude that a configuration utilising query rewriting along with reranking delivers the best results. The code is available on GitHub https://github.com/merttoprak1/MTRAGEval-Evaluating-Multi-Turn-RAG-Conversations.
%U https://aclanthology.org/2026.semeval-1.309/
%P 2447-2455
Markdown (Informal)
[Polito Team at SemEval-2026 Task 8: Scaling Multi-Turn RAG: High-Performance Parallelized Pipeline for the MTRAG Benchmark](https://aclanthology.org/2026.semeval-1.309/) (Çelik et al., SemEval 2026)
ACL
- Murat Çelik, Nejla Dinçer, Can Ersoy, Mert Toprak, Barış Ünal, Riccardo Coppola, and Flavio Giobergia. 2026. Polito Team at SemEval-2026 Task 8: Scaling Multi-Turn RAG: High-Performance Parallelized Pipeline for the MTRAG Benchmark. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 2447–2455, San Diego, California, USA. Association for Computational Linguistics.