@inproceedings{chernogorskii-etal-2026-dragon,
title = "{DRAGO}n: Designing {RAG} On Periodically Updated Corpus",
author = "Chernogorskii, Fedor and
Averkiev, Sergei and
Kudraleeva, Liliya and
Martirosian, Zaven and
Tikhonova, Maria and
Malykh, Valentin and
Fenogenova, Alena",
editor = "Baez Santamaria, Selene and
Somayajula, Sai Ashish and
Yamaguchi, Atsuki",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 4: Student Research Workshop)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-srw.48/",
pages = "622--638",
ISBN = "979-8-89176-383-8",
abstract = "This paper introduces \textbf{DRAGOn}, method to design a RAG benchmark on a regularly updated corpus. It features recent reference datasets, a question generation framework, an automatic evaluation pipeline, and a public leaderboard.Specified reference datasets allow for uniform comparison of RAG systems, while newly generated dataset versions mitigate data leakage and ensure that all models are evaluated on unseen, comparable data.The pipeline for automatic question generation extracts the Knowledge Graph from the text corpus and produces multiple question-answer pairs utilizing modern LLM capabilities.A set of diverse LLM-as-Judge metrics is provided for a comprehensive model evaluation.We used Russian news outlets to form the datasets and demonstrate our methodology. We launch a public leaderboard to track the development of RAG systems and encourage community participation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chernogorskii-etal-2026-dragon">
<titleInfo>
<title>DRAGOn: Designing RAG On Periodically Updated Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fedor</namePart>
<namePart type="family">Chernogorskii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergei</namePart>
<namePart type="family">Averkiev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liliya</namePart>
<namePart type="family">Kudraleeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaven</namePart>
<namePart type="family">Martirosian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Tikhonova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alena</namePart>
<namePart type="family">Fenogenova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Selene</namePart>
<namePart type="family">Baez Santamaria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Ashish</namePart>
<namePart type="family">Somayajula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsuki</namePart>
<namePart type="family">Yamaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-383-8</identifier>
</relatedItem>
<abstract>This paper introduces DRAGOn, method to design a RAG benchmark on a regularly updated corpus. It features recent reference datasets, a question generation framework, an automatic evaluation pipeline, and a public leaderboard.Specified reference datasets allow for uniform comparison of RAG systems, while newly generated dataset versions mitigate data leakage and ensure that all models are evaluated on unseen, comparable data.The pipeline for automatic question generation extracts the Knowledge Graph from the text corpus and produces multiple question-answer pairs utilizing modern LLM capabilities.A set of diverse LLM-as-Judge metrics is provided for a comprehensive model evaluation.We used Russian news outlets to form the datasets and demonstrate our methodology. We launch a public leaderboard to track the development of RAG systems and encourage community participation.</abstract>
<identifier type="citekey">chernogorskii-etal-2026-dragon</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-srw.48/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>622</start>
<end>638</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DRAGOn: Designing RAG On Periodically Updated Corpus
%A Chernogorskii, Fedor
%A Averkiev, Sergei
%A Kudraleeva, Liliya
%A Martirosian, Zaven
%A Tikhonova, Maria
%A Malykh, Valentin
%A Fenogenova, Alena
%Y Baez Santamaria, Selene
%Y Somayajula, Sai Ashish
%Y Yamaguchi, Atsuki
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-383-8
%F chernogorskii-etal-2026-dragon
%X This paper introduces DRAGOn, method to design a RAG benchmark on a regularly updated corpus. It features recent reference datasets, a question generation framework, an automatic evaluation pipeline, and a public leaderboard.Specified reference datasets allow for uniform comparison of RAG systems, while newly generated dataset versions mitigate data leakage and ensure that all models are evaluated on unseen, comparable data.The pipeline for automatic question generation extracts the Knowledge Graph from the text corpus and produces multiple question-answer pairs utilizing modern LLM capabilities.A set of diverse LLM-as-Judge metrics is provided for a comprehensive model evaluation.We used Russian news outlets to form the datasets and demonstrate our methodology. We launch a public leaderboard to track the development of RAG systems and encourage community participation.
%U https://aclanthology.org/2026.eacl-srw.48/
%P 622-638
Markdown (Informal)
[DRAGOn: Designing RAG On Periodically Updated Corpus](https://aclanthology.org/2026.eacl-srw.48/) (Chernogorskii et al., EACL 2026)
ACL
- Fedor Chernogorskii, Sergei Averkiev, Liliya Kudraleeva, Zaven Martirosian, Maria Tikhonova, Valentin Malykh, and Alena Fenogenova. 2026. DRAGOn: Designing RAG On Periodically Updated Corpus. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 622–638, Rabat, Morocco. Association for Computational Linguistics.