@inproceedings{ranaldi-etal-2025-improving-multilingual,
title = "Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations",
author = "Ranaldi, Leonardo and
Ranaldi, Federico and
Zanzotto, Fabio Massimo and
Haddow, Barry and
Birch, Alexandra",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.461/",
doi = "10.18653/v1/2025.emnlp-main.461",
pages = "9064--9085",
ISBN = "979-8-89176-332-6",
abstract = "Retrieval-augmented generation (RAG) is key to improving large language models (LLMs) in systematically accessing richer factual knowledge. Yet, using RAG mechanisms brings intrinsic challenges, as LLMs must deal with conflicting knowledge, especially in multilingual retrieval, where the heterogeneity of knowledge retrieved may deliver different outlooks. To make RAG more analytical, critical and grounded, we introduce \textit{Dialectic-RAG} (\textit{D}-RAG), a modular approach guided by \textit{Argumentative Explanations}, i.e., structured reasoning process that systematically evaluates retrieved information by comparing, contrasting, and resolving conflicting perspectives. Given a query and a set of multilingual related documents, \textit{D}-RAG selects and exemplifies relevant knowledge for delivering dialectic explanations that, by critically weighing opposing arguments and filtering extraneous content, clearly determine the final response. We show the impact of our framework both as an in-context learning strategy and for constructing demonstrations to instruct smaller models. Our experiments demonstrate that \textit{D}-RAG significantly improves RAG approaches, requiring low-impact computational effort and providing robustness to knowledge perturbations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ranaldi-etal-2025-improving-multilingual">
<titleInfo>
<title>Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="family">Ranaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Ranaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="given">Massimo</namePart>
<namePart type="family">Zanzotto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</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 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Retrieval-augmented generation (RAG) is key to improving large language models (LLMs) in systematically accessing richer factual knowledge. Yet, using RAG mechanisms brings intrinsic challenges, as LLMs must deal with conflicting knowledge, especially in multilingual retrieval, where the heterogeneity of knowledge retrieved may deliver different outlooks. To make RAG more analytical, critical and grounded, we introduce Dialectic-RAG (D-RAG), a modular approach guided by Argumentative Explanations, i.e., structured reasoning process that systematically evaluates retrieved information by comparing, contrasting, and resolving conflicting perspectives. Given a query and a set of multilingual related documents, D-RAG selects and exemplifies relevant knowledge for delivering dialectic explanations that, by critically weighing opposing arguments and filtering extraneous content, clearly determine the final response. We show the impact of our framework both as an in-context learning strategy and for constructing demonstrations to instruct smaller models. Our experiments demonstrate that D-RAG significantly improves RAG approaches, requiring low-impact computational effort and providing robustness to knowledge perturbations.</abstract>
<identifier type="citekey">ranaldi-etal-2025-improving-multilingual</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.461</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.461/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>9064</start>
<end>9085</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations
%A Ranaldi, Leonardo
%A Ranaldi, Federico
%A Zanzotto, Fabio Massimo
%A Haddow, Barry
%A Birch, Alexandra
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F ranaldi-etal-2025-improving-multilingual
%X Retrieval-augmented generation (RAG) is key to improving large language models (LLMs) in systematically accessing richer factual knowledge. Yet, using RAG mechanisms brings intrinsic challenges, as LLMs must deal with conflicting knowledge, especially in multilingual retrieval, where the heterogeneity of knowledge retrieved may deliver different outlooks. To make RAG more analytical, critical and grounded, we introduce Dialectic-RAG (D-RAG), a modular approach guided by Argumentative Explanations, i.e., structured reasoning process that systematically evaluates retrieved information by comparing, contrasting, and resolving conflicting perspectives. Given a query and a set of multilingual related documents, D-RAG selects and exemplifies relevant knowledge for delivering dialectic explanations that, by critically weighing opposing arguments and filtering extraneous content, clearly determine the final response. We show the impact of our framework both as an in-context learning strategy and for constructing demonstrations to instruct smaller models. Our experiments demonstrate that D-RAG significantly improves RAG approaches, requiring low-impact computational effort and providing robustness to knowledge perturbations.
%R 10.18653/v1/2025.emnlp-main.461
%U https://aclanthology.org/2025.emnlp-main.461/
%U https://doi.org/10.18653/v1/2025.emnlp-main.461
%P 9064-9085
Markdown (Informal)
[Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations](https://aclanthology.org/2025.emnlp-main.461/) (Ranaldi et al., EMNLP 2025)
ACL