@inproceedings{von-daniken-etal-2026-c4,
title = "C4: A Multilingual Benchmark for Retrieval-Augmented Generation Based on the Catechism of the Catholic Church and Its Compendium",
author = {von D{\"a}niken, Pius and
Cieliebak, Mark and
Deriu, Jan},
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.590/",
doi = "10.63317/5a8nuzcc3cq3",
pages = "7446--7456",
abstract = "We introduce a new multilingual case study for evaluating retrieval augmented generation (RAG) systems, based on the Catechism of the Catholic Church and its Compendium. The Catechism is a structured document with numbered paragraphs, officially translated into many languages under strict editorial alignment. The Compendium reformulates this material into a question-answer format with explicit citations to the corresponding paragraphs. Together, they form a set of parallel monolingual corpora that share identical semantic structure, enabling direct, controlled comparison of RAG performance across languages. Beyond its theological origin, this text pair closely mirrors real-world applications of RAG in institutional contexts, such as querying internal policy documents with associated FAQ-style summaries, making it a practical testbed for multilingual retrieval and grounded answer generation. We release our data collection scripts and baseline results for further research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="von-daniken-etal-2026-c4">
<titleInfo>
<title>C4: A Multilingual Benchmark for Retrieval-Augmented Generation Based on the Catechism of the Catholic Church and Its Compendium</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pius</namePart>
<namePart type="family">von Däniken</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Cieliebak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Deriu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a new multilingual case study for evaluating retrieval augmented generation (RAG) systems, based on the Catechism of the Catholic Church and its Compendium. The Catechism is a structured document with numbered paragraphs, officially translated into many languages under strict editorial alignment. The Compendium reformulates this material into a question-answer format with explicit citations to the corresponding paragraphs. Together, they form a set of parallel monolingual corpora that share identical semantic structure, enabling direct, controlled comparison of RAG performance across languages. Beyond its theological origin, this text pair closely mirrors real-world applications of RAG in institutional contexts, such as querying internal policy documents with associated FAQ-style summaries, making it a practical testbed for multilingual retrieval and grounded answer generation. We release our data collection scripts and baseline results for further research.</abstract>
<identifier type="citekey">von-daniken-etal-2026-c4</identifier>
<identifier type="doi">10.63317/5a8nuzcc3cq3</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.590/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>7446</start>
<end>7456</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T C4: A Multilingual Benchmark for Retrieval-Augmented Generation Based on the Catechism of the Catholic Church and Its Compendium
%A von Däniken, Pius
%A Cieliebak, Mark
%A Deriu, Jan
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F von-daniken-etal-2026-c4
%X We introduce a new multilingual case study for evaluating retrieval augmented generation (RAG) systems, based on the Catechism of the Catholic Church and its Compendium. The Catechism is a structured document with numbered paragraphs, officially translated into many languages under strict editorial alignment. The Compendium reformulates this material into a question-answer format with explicit citations to the corresponding paragraphs. Together, they form a set of parallel monolingual corpora that share identical semantic structure, enabling direct, controlled comparison of RAG performance across languages. Beyond its theological origin, this text pair closely mirrors real-world applications of RAG in institutional contexts, such as querying internal policy documents with associated FAQ-style summaries, making it a practical testbed for multilingual retrieval and grounded answer generation. We release our data collection scripts and baseline results for further research.
%R 10.63317/5a8nuzcc3cq3
%U https://aclanthology.org/2026.lrec-1.590/
%U https://doi.org/10.63317/5a8nuzcc3cq3
%P 7446-7456
Markdown (Informal)
[C4: A Multilingual Benchmark for Retrieval-Augmented Generation Based on the Catechism of the Catholic Church and Its Compendium](https://aclanthology.org/2026.lrec-1.590/) (von Däniken et al., LREC 2026)
ACL