@inproceedings{van-drie-etal-2026-quala,
title = "{Q}u{ALA}-{NL}: Question {\&} Answer with Legal Attribution in {D}utch",
author = "van Drie, Romy A.N. and
Bakker, Roos M. and
Di Scala, Daan L. and
de Boer, Maaike",
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-1.49/",
doi = "10.63317/5i9bqybga69e",
pages = "674--684",
abstract = "Ensuring trustworthy and traceable outputs from Large Language Models (LLMs) is crucial in high-stakes domains such as law. Retrieval-Augmented Generation (RAG) offers a way to enhance LLMs with domain-specific or updated information and provide attribution to the source, and recent work has focused on knowledge-based RAG (K-RAG) for improved factual grounding. However, proper evaluation of such systems requires high-quality datasets. To address this need, we introduce QuALA-NL: a dataset that provides attributions to legal formalizations, enabling experiments with K-RAG in the legal domain. The dataset contains 101 QA pairs on three Dutch laws, with attributions to the law text and a formalization of the interpretation of the legal text. To demonstrate the capabilities of the dataset, we perform experiments using four configurations: LLM-only, RAG using legal texts, K-RAG using a formalization of the legal texts, and RAG combining both legal texts and the formalizations. The results show that K-RAG has the highest retrieval scores, but that this method is outperformed by text-based RAG on generation. A qualitative analysis shows that the use of the knowledge graph for the generation of answers can be improved. QuALA-NL can be used in future work to experiment with knowledge-based Retrieval Augmented Generation methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-drie-etal-2026-quala">
<titleInfo>
<title>QuALA-NL: Question & Answer with Legal Attribution in Dutch</title>
</titleInfo>
<name type="personal">
<namePart type="given">Romy</namePart>
<namePart type="given">A.N.</namePart>
<namePart type="family">van Drie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roos</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Bakker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daan</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Di Scala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maaike</namePart>
<namePart type="family">de Boer</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>Ensuring trustworthy and traceable outputs from Large Language Models (LLMs) is crucial in high-stakes domains such as law. Retrieval-Augmented Generation (RAG) offers a way to enhance LLMs with domain-specific or updated information and provide attribution to the source, and recent work has focused on knowledge-based RAG (K-RAG) for improved factual grounding. However, proper evaluation of such systems requires high-quality datasets. To address this need, we introduce QuALA-NL: a dataset that provides attributions to legal formalizations, enabling experiments with K-RAG in the legal domain. The dataset contains 101 QA pairs on three Dutch laws, with attributions to the law text and a formalization of the interpretation of the legal text. To demonstrate the capabilities of the dataset, we perform experiments using four configurations: LLM-only, RAG using legal texts, K-RAG using a formalization of the legal texts, and RAG combining both legal texts and the formalizations. The results show that K-RAG has the highest retrieval scores, but that this method is outperformed by text-based RAG on generation. A qualitative analysis shows that the use of the knowledge graph for the generation of answers can be improved. QuALA-NL can be used in future work to experiment with knowledge-based Retrieval Augmented Generation methods.</abstract>
<identifier type="citekey">van-drie-etal-2026-quala</identifier>
<identifier type="doi">10.63317/5i9bqybga69e</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.49/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>674</start>
<end>684</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QuALA-NL: Question & Answer with Legal Attribution in Dutch
%A van Drie, Romy A.N.
%A Bakker, Roos M.
%A Di Scala, Daan L.
%A de Boer, Maaike
%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 van-drie-etal-2026-quala
%X Ensuring trustworthy and traceable outputs from Large Language Models (LLMs) is crucial in high-stakes domains such as law. Retrieval-Augmented Generation (RAG) offers a way to enhance LLMs with domain-specific or updated information and provide attribution to the source, and recent work has focused on knowledge-based RAG (K-RAG) for improved factual grounding. However, proper evaluation of such systems requires high-quality datasets. To address this need, we introduce QuALA-NL: a dataset that provides attributions to legal formalizations, enabling experiments with K-RAG in the legal domain. The dataset contains 101 QA pairs on three Dutch laws, with attributions to the law text and a formalization of the interpretation of the legal text. To demonstrate the capabilities of the dataset, we perform experiments using four configurations: LLM-only, RAG using legal texts, K-RAG using a formalization of the legal texts, and RAG combining both legal texts and the formalizations. The results show that K-RAG has the highest retrieval scores, but that this method is outperformed by text-based RAG on generation. A qualitative analysis shows that the use of the knowledge graph for the generation of answers can be improved. QuALA-NL can be used in future work to experiment with knowledge-based Retrieval Augmented Generation methods.
%R 10.63317/5i9bqybga69e
%U https://aclanthology.org/2026.lrec-1.49/
%U https://doi.org/10.63317/5i9bqybga69e
%P 674-684
Markdown (Informal)
[QuALA-NL: Question & Answer with Legal Attribution in Dutch](https://aclanthology.org/2026.lrec-1.49/) (van Drie et al., LREC 2026)
ACL
- Romy A.N. van Drie, Roos M. Bakker, Daan L. Di Scala, and Maaike de Boer. 2026. QuALA-NL: Question & Answer with Legal Attribution in Dutch. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 674–684, Palma de Mallorca, Spain. ELRA Language Resource Association.