<!DOCTYPE html>
<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body>
<div class="moz-forward-container">
<div class="moz-forward-container">
<p>-----------------------------------------------------------------------------
<br>
<br>
Call for submissions <br>
<br>
1st International Workshop on Quality in Large Language Models
and Knowledge Graphs <br>
In conjunction with EDBT/ICDT 2026 <br>
<br>
QuaLLM-KG @ EDBT/ICDT 2026 <br>
24 March 2026, Tampere, Finland <br>
<br>
Website: <a class="moz-txt-link-freetext"
href="https://quallmkg2026.github.io/"
moz-do-not-send="true">https://quallmkg2026.github.io/</a></p>
<p><b>New deadline: January 25th AoE</b><br>
-----------------------------------------------------------------------------
<br>
<br>
**** Goal **** <br>
<br>
QuaLLM-KG aims to bring together researchers and practitioners
working on quality issues at the intersection of large
language models and knowledge graphs. The workshop focuses on
theories, methods, and applications for assessing, improving,
and monitoring the quality of LLMs and KGs. <br>
<br>
<br>
**** Important Dates **** <br>
<br>
- Submission deadline: January 25th, 2026 <br>
- Notification: February 8th, 2026 <br>
- Camera-ready: February 20th, 2026 <br>
<br>
<br>
**** Topics **** <br>
<br>
* Quality in Knowledge Graphs <br>
- Accuracy, consistency, completeness, freshness <br>
- Schema validation, constraint checking, error detection <br>
- Entity resolution, link prediction, ontology alignment <br>
- Provenance, explainability, trust in KG data <br>
- KG quality in dynamic and large-scale settings <br>
* Quality in Large Language Models <br>
- Hallucination reduction & factual grounding <br>
- Bias detection and mitigation <br>
- Metrics & benchmarks for quality assessment <br>
- Uncertainty estimation, calibration, interpretability <br>
* Synergies Between KGs and LLMs <br>
- KG-based grounding and fact-checking for LLMs <br>
- LLM-based KG enrichment, extraction, entity linking <br>
- Quality-driven prompting and fine-tuning <br>
- Hybrid KG–LLM architectures for quality assurance <br>
- Evaluation frameworks for integration and consistency <br>
* Benchmarks and Evaluation Frameworks <br>
- Datasets and metrics for KG & LLM quality <br>
- Tools for monitoring, validation, maintenance <br>
- Reproducibility, transparency, responsible AI <br>
* Applications and Case Studies <br>
- Scientific, industrial, enterprise use cases <br>
- Quality at scale <br>
- Human-in-the-loop quality control <br>
<br>
**** Submissions **** <br>
<br>
We invite submissions of full papers (up to 8 pages, excluding
references) and short papers describing work in progress,
systems, demos/systems/applications, <br>
or vision/innovative ideas (up to 4 pages, excluding
references). <br>
<br>
Submissions should be in the CEUR-WS proceedings template. <br>
<br>
Accepted papers will be published in the CEUR Workshop
proceedings (CEUR-WS.org). <br>
<br>
**** Workshop Organizers **** <br>
<br>
- Soror Sahri, Université Paris Cité, France <br>
- Sven Groppe, University of Lübeck, Germany <br>
- Farah Benamara, IPAL-CNRS, Singapore & University of
Toulouse</p>
<p><br>
</p>
<pre class="moz-signature" cols="72">--
========================
Farah Benamara Zitoune
Professor in Computer Science, Université de Toulouse
IRIT and IPAL-CNRS Singapore
118 Route de Narbonne, 31062, Toulouse.
Tel : +33 5 61 55 77 06
<a class="moz-txt-link-freetext"
href="http://www.irit.fr/~Farah.Benamara" moz-do-not-send="true">http://www.irit.fr/~Farah.Benamara</a>
==================================</pre>
</div>
</div>
</body>
</html>