CLEAR-AI Workshop · IJCAI-ECAI 2026 · Bremen, Germany

CLEAR — Collaborative Methods and Tools for
Engineering and Evaluating Transparency in AI

CLEAR-AI Workshop  ·  Bremen, Germany  ·  16 August 2026

Submissions openMarch 23, 2026, 09:00 (GMT+1)
Paper submission deadlineMay 20, 2026 (AOE)
Notification of acceptanceJune 10, 2026 (AOE)
Deadline for camera-readyJuly 15, 2026 (AOE)

The CLEAR-AI Workshop brings together researchers, practitioners, and stakeholders to address transparency in AI systems through collaborative and participatory approaches. Below you'll find more details about the workshop's focus, its programme, and the submission guidelines.

As AI systems become integral to critical decision-making processes, ensuring their transparency, fairness, and accountability is more essential than ever. The AI Act, the world's first attempt to systematically regulate artificial intelligence, places significant emphasis on this need. In particular, the Act establishes transparency as a fundamental principle, aiming to safeguard user rights and foster trust and reliability in new technologies.

Achieving these objectives necessitates not only the establishment of robust technical frameworks but also the active engagement of a diverse range of stakeholders to ensure that the development of AI is aligned with societal values. The CLEAR-AI Workshop addresses the critical need for interdisciplinary collaboration to advance methods, tools, and evaluation frameworks that ensure transparency, fairness, and trustworthiness in AI systems.

The workshop took place on 16 August 2026 in Bremen, Germany.

It was co-located with IJCAI-ECAI 2026 — International Joint Conference on Artificial Intelligence (15–21 August 2026).

Slot 1 — Opening & Keynote
09:00 – 10:30
Welcome, Introduction & Practicalities
Overview of the workshop programme and logistics

Keynote
Mattias Brännström, Umeå University

Introduction to Challenge 1
Reframing Transparency as a Relation, Not a Static Property
10:30 – 11:00
☕ Coffee Break
Slot 2 — Challenge 1: Papers & Panel
11:00 – 12:30
Paper“Just to be Clear?” — Experiments with bibliometric visualizations for interdisciplinary conversations about key terms in AI Ethics

PaperAutomated Verification of Reproducibility Reporting in AI Research

PaperDeBERTa-Sentinel: Toward Transparent and Trustworthy Detection of AI-Generated Text

PaperXAI-Safety-Judge: A Domain-Adaptable Explanation-Alignment Evaluation Environment for Safety-Critical Models

PanelPanel Discussion — Challenge 1
12:30 – 14:00
🍽️ Lunch Break
Slot 3 — Challenge 2: Papers & Panel
14:00 – 15:30
Introduction to Challenge 2
Connecting Methods to Meaning and Purpose

PaperDomain-Aware Quality Evaluation for Symbolic Knowledge

PaperShadow Technical Debt: The Dark Matter of Engineered Systems

PanelPanel Discussion — Challenge 2
15:30 – 16:00
☕ Coffee Break
Slot 4 — Challenge 3: Papers, Panel & Closing
16:00 – 17:30
Introduction to Challenge 3
Moving Toward Stakeholder-Centered Transparency

PaperHow You Implement Matters: Navigating the XAI Implementation Journey

PaperVerification Burden as Stakeholder-Centered Transparency: Evaluating Legal AI for Access-to-Justice Users

PanelPanel Discussion — Challenge 3

PanelGeneral Panel Discussion

Transparency takes up a central instrumental role in addressing and understanding a wide range of problems from legal to ethical in AI development and deployment. Yet, transparency is often a vague and hard to pin down notion from an objective perspective and is defined differently on different levels in the understanding of AI systems.

In CLEAR we want to approach the problem from the direction of stakeholder needs on transparency. By understanding the needs for information we can work to concretely meet these demands.

The needs on transparency can come from many different sources, such as legal understanding and effective user agency, as such any workable method for this will have to address the participatory aspect of eliciting these needs from the stakeholders.

Challenge 1

Reframing Transparency as a Relation, Not a Static Property

Transparency is too often treated as something systems have rather than something they provide in relation to those who use, audit, or are affected by them. This theme challenges us to rethink transparency as an active relation between information and its audience.

Challenge 2

Connecting Methods to Meaning and Purpose

Technical tools and conceptual models for transparency abound, but they often operate without a clear sense of for whom and for what they exist. This theme explores how metrics, explanations, and frameworks can be oriented toward concrete purposes—whether legal accountability, informed oversight, or effective user understanding.

Challenge 3

Moving Toward Stakeholder-Centered Transparency

The ultimate challenge remains to make transparency usable, relevant, and responsive. This theme looks at how today's methods can evolve—through participatory, methodological, or institutional innovation—toward transparency that genuinely empowers those who depend on it.

Submissions are now closed. Accepted papers are currently being processed for the proceedings.

Authors were invited to submit papers of up to 15 pages (excluding references) following the CEUR-WS formatting requirements. The proceedings will be submitted to CEUR-WS.org for online publication.

Submissions were reviewed by at least two reviewers and had to be fully anonymised, with all author names, affiliations, and identifying references removed. At least one author of each accepted paper was required to register for the workshop and for IJCAI-ECAI 2026.

Submissions were handled through OpenReview.

Themis Dimitra Xanthopoulou
Dept. of Computing Science, Umeå University
Rachele Carli
Dept. of Computing Science, Umeå University
Andreas Brännström
Dept. of Computing Science, Umeå University
Francien Dechesne
eLaw Center for Law and Digital Technologies, Leiden University
Chiara Gallese
Tilburg University
Mattias Brännström
Dept. of Computing Science, Umeå University
Virginia Dignum
AI Policy Lab
Federica Casarosa
Scuola Superiore Sant'Anna Pisa
Karni Chagal-Feferkorn
University of South Florida
Atia Cortés
Barcelona Supercomputing Center
Stefania Costantini
University of L'Aquila
Jayati Deshmukh
BITS Pilani – Birla Institute of Technology and Science
Elena Falletti
Carlo Cattaneo University
Francesca Gennari
Sant'Anna School of Advanced Studies
Marta Infantino
University of Trieste
Nicole Inverardi
University of Milan – Bicocca
Francesca Rotolo
University of Venice
Sofia Santinello
Tilburg University
Kshitiz Verma
JK Lakshmipat University Jaipur

Questions about the workshop or the proceedings are best sent to the Organising Committee.