@inproceedings{yu-adelani-2025-training,
title = "Training of {LLM}-Based List-Wise Multilingual Reranker",
author = "Yu, Hao and
Adelani, David Ifeoluwa",
editor = "Adelani, David Ifeoluwa and
Arnett, Catherine and
Ataman, Duygu and
Chang, Tyler A. and
Gonen, Hila and
Raja, Rahul and
Schmidt, Fabian and
Stap, David and
Wang, Jiayi",
booktitle = "Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)",
month = nov,
year = "2025",
address = "Suzhuo, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.mrl-main.42/",
pages = "652--663",
ISBN = "979-8-89176-345-6",
abstract = "Multilingual retrieval-augmented generation (MRAG) systems heavily rely on robust Information Retrieval (IR). Reranking as a key component optimizes the initially retrieved document set to present the most pertinent information to the generative model, addressing context limitations and minimizing hallucinations. We propose an approach that trains Large Language Models (LLMs) as multilingual listwise rerankers through supervised fine-tuning (SFT) on a diverse mixture of multilingual and extended English ranking examples, and enhancing reasoning capabilities through Direct Preference Optimization (DPO) from translated task-specific reasoning processes. Experiments demonstrate that the approach improves accuracy@5 by 20-30{\%} across all six high- mediumand low-resource languages compared to the BM25. The posted training 1B models achieve comparable performance to 7B baseline models while enabling faster inference. Finally, we investigate the effectiveness of different reasoning strategies in DPO with crosslingual and monolingual thinking processes."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-adelani-2025-training">
<titleInfo>
<title>Training of LLM-Based List-Wise Multilingual Reranker</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Arnett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duygu</namePart>
<namePart type="family">Ataman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hila</namePart>
<namePart type="family">Gonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Raja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabian</namePart>
<namePart type="family">Schmidt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Stap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhuo, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-345-6</identifier>
</relatedItem>
<abstract>Multilingual retrieval-augmented generation (MRAG) systems heavily rely on robust Information Retrieval (IR). Reranking as a key component optimizes the initially retrieved document set to present the most pertinent information to the generative model, addressing context limitations and minimizing hallucinations. We propose an approach that trains Large Language Models (LLMs) as multilingual listwise rerankers through supervised fine-tuning (SFT) on a diverse mixture of multilingual and extended English ranking examples, and enhancing reasoning capabilities through Direct Preference Optimization (DPO) from translated task-specific reasoning processes. Experiments demonstrate that the approach improves accuracy@5 by 20-30% across all six high- mediumand low-resource languages compared to the BM25. The posted training 1B models achieve comparable performance to 7B baseline models while enabling faster inference. Finally, we investigate the effectiveness of different reasoning strategies in DPO with crosslingual and monolingual thinking processes.</abstract>
<identifier type="citekey">yu-adelani-2025-training</identifier>
<location>
<url>https://aclanthology.org/2025.mrl-main.42/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>652</start>
<end>663</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Training of LLM-Based List-Wise Multilingual Reranker
%A Yu, Hao
%A Adelani, David Ifeoluwa
%Y Adelani, David Ifeoluwa
%Y Arnett, Catherine
%Y Ataman, Duygu
%Y Chang, Tyler A.
%Y Gonen, Hila
%Y Raja, Rahul
%Y Schmidt, Fabian
%Y Stap, David
%Y Wang, Jiayi
%S Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhuo, China
%@ 979-8-89176-345-6
%F yu-adelani-2025-training
%X Multilingual retrieval-augmented generation (MRAG) systems heavily rely on robust Information Retrieval (IR). Reranking as a key component optimizes the initially retrieved document set to present the most pertinent information to the generative model, addressing context limitations and minimizing hallucinations. We propose an approach that trains Large Language Models (LLMs) as multilingual listwise rerankers through supervised fine-tuning (SFT) on a diverse mixture of multilingual and extended English ranking examples, and enhancing reasoning capabilities through Direct Preference Optimization (DPO) from translated task-specific reasoning processes. Experiments demonstrate that the approach improves accuracy@5 by 20-30% across all six high- mediumand low-resource languages compared to the BM25. The posted training 1B models achieve comparable performance to 7B baseline models while enabling faster inference. Finally, we investigate the effectiveness of different reasoning strategies in DPO with crosslingual and monolingual thinking processes.
%U https://aclanthology.org/2025.mrl-main.42/
%P 652-663
Markdown (Informal)
[Training of LLM-Based List-Wise Multilingual Reranker](https://aclanthology.org/2025.mrl-main.42/) (Yu & Adelani, MRL 2025)
ACL