Overview • Topics • CFP • Dates • Submission • Keynotes • Program • Organizers • Previous Editions • Contact

Overview

The workshop Smarter Extraction of ScholArly MEtadata using Knowledge Graphs, Language Models and Agents (SESAME) brings together researchers and practitioners interested in improving scholarly metadata through large language models, Agents, knowledge graphs, natural language processing, and linked-data technologies.

High-quality scholarly metadata is essential for search, discovery, research assessment, reproducibility, and the long-term operation of digital-library infrastructures. However, metadata about publications, authors, affiliations, datasets, software, models, citations, and other research objects is frequently incomplete, inconsistent, or distributed across heterogeneous sources.

SESAME focuses on methods that combine language models and structured knowledge to support reliable metadata extraction, normalization, enrichment, linking, validation, and evaluation. The workshop provides a platform for researchers, digital-library professionals, data curators, infrastructure providers, and policy experts to exchange methods, datasets, systems, evaluation practices, and lessons learned.

The workshop particularly welcomes work connecting large language models with linked data and knowledge graphs for tasks such as author disambiguation, affiliation normalization, citation-context understanding, persistent-identifier linking, provenance tracking, and transparent metadata curation.

Topics of Interest

Topics include, but are not limited to:

Call for Papers

SESAME 2026 invites original research contributions addressing the above listed topics in three categories.

Important Dates (AoE)

All deadlines will use Anywhere on Earth (AoE) time.

Submission

Submissions should contain original work and should not be simultaneously under review elsewhere.

Submit Paper

Keynote Speakers

Dr Angelo Salatino
Research Fellow at the Knowledge Media Institute
The Open University, United Kingdom

Keynote Title:
Sprinkling Semantics and AI into Metascience

Abstract:
This talk explores the role of Artificial Intelligence and Semantic Web technologies in the field of metascience, focusing on how these computational methods can be used to better understand and optimise the research ecosystem. While traditional methods of categorising and analysing scientific progress often rely on manual curation that is difficult to scale, we introduce innovative AI-driven frameworks designed to automatically generate fine-grained representations of research knowledge. By leveraging large-scale ontologies and machine learning models, our work facilitates the tracking of research trends, the identification of knowledge flows between academia and industry, and the acceleration of progress through automated literature synthesis. Ultimately, this research aims to provide evidence-based insights that can inform funding strategies and national research policies, ensuring that transformative ideas are identified and supported more effectively.

Prof. Dr. Ingo Frommholz
Professor at School of Applied Data Science
Modul University Vienna, Austria

Keynote Title:
"Fake Science" and Information Overload in Academia

Abstract:
Scientific communication is experiencing unprecedented growth, with publication volumes increasing at a scale that overwhelms researchers’ capacity to process and evaluate information. This information overload is not only a byproduct of legitimate scholarly activity but is increasingly driven by low-quality and even fraudulent content. This poses both critical challenges and unique opportunities for the Information Retrieval and Digital Libraries communities. On the one hand, information overload and quality degradation pose a challenge that needs to be addressed more directly by retrieval models that, traditionally, are mainly considering topical relevance. On the other hand, advances in AI, NLP, and bibliometric-enhanced retrieval offer promising directions for filtering, ranking, and contextualising scholarly information. In this talk, we will examine the evolving problem of fake science and its role in driving information overload. We will outline recent developments in scholarly information access, highlight open research problems — from detecting low-quality and fraudulent content to designing veracity-aware retrieval and recommendation models — and discuss how IR research can contribute to ensuring that high-quality knowledge remains discoverable, trustworthy, and actionable in an era of overwhelming information abundance.

Program

The SESAME 2026 workshop will take place on 16 October 2026. The workshop program includes invited keynote talks, research paper presentations, an invited talk, and an interactive discussion session.

Description US Central (Texas) Germany / Austria / Italy UK China
Opening & Welcome 09:00–09:15 16:00–16:15 15:00–15:15 22:00–22:15
Keynote 1
Sprinkling Semantics and AI into Metascience 		09:15–10:00 16:15–17:00 15:15–16:00 22:15–23:00
Submission ID-5
Multi-Agent Research Interest Discovery for Scientific Paper Recommendation 		10:00–10:30 17:00–17:30 16:00–16:30 23:00–23:30
Submission ID-1
The Impact of Keyword-Based Weak Supervision on Technology-Assisted Review Performance 		10:30–11:00 17:30–18:00 16:30–17:00 23:30–00:00
Short Break 11:00–11:15 18:00–18:15 17:00–17:15 00:00–00:15 (+1 day)
Keynote 2
"Fake Science" and Information Overload in Academia 		11:15–12:00 18:15–19:00 17:15–18:00 00:15–01:00 (+1 day)
Submission ID-6
Layered Assurance for Knowledge-Graph-Mediated Newspaper Metadata: Traceable Checks, Identity Audit, and Evaluator Dependence 		12:00–12:30 19:00–19:30 18:00–18:30 01:00–01:30 (+1 day)
Submission ID-7
Reconstructing Systematic-Review Data Tables with Large Language Model Extraction: A Commensurability Study 		12:30–13:00 19:30–20:00 18:30–19:00 01:30–02:00 (+1 day)
Short Break 13:00–13:30 20:00–20:30 19:00–19:30 02:00–02:30 (+1 day)
Submission ID-8
ETD-ASC: Abstract Sentence Classification for Electronic Theses and Dissertations 		13:30–14:00 20:30–21:00 19:30–20:00 02:30–03:00 (+1 day)
Challenges for Metadata Extraction in Agentic Era 14:00–15:00 21:00–22:00 20:00–21:00 03:00–04:00 (+1 day)
Discussion 15:00–15:30 22:00–22:30 21:00–21:30 04:00–04:30 (+1 day)
Closing Remarks 15:30–15:40 22:30–22:40 21:30–21:40 04:30–04:40 (+1 day)

Time Zone Disclaimer: The times listed above are provided for reference. Due to differences in daylight saving time and regional time-zone changes, presenters and participants are kindly requested to verify the corresponding time in their local time zone before the workshop. US Central (Texas) time should be considered the reference time for the workshop schedule.

Organizers

Dr. Muhammad Asif Suryani
Knowledge Technologies for the Social Sciences (KTS),
GESIS – Leibniz Institute for the Social Sciences, Cologne, Germany

Dr. Brigitte Mathiak
Knowledge Technologies for the Social Sciences (KTS),
GESIS – Leibniz Institute for the Social Sciences, Cologne, Germany

Dr. Florian Reitz
Schloss Dagstuhl – Leibniz Center for Informatics,
Wadern, Germany

Dr. Florian Jäckel
Schloss Dagstuhl – Leibniz Center for Informatics,
Wadern, Germany

Florian Hauss
Data Science and Big Data Analytics,
Ulm University, Ulm, Germany

Prof. Dr. Ansgar Scherp
Data Science and Big Data Analytics,
Ulm University, Ulm, Germany

Program Committee

Dr. Marcel R. Ackermann
DBLP computer science bibliography,
University of Trier, Germany, Germany

Dr. Kanishka Silva
Knowledge Technologies for the Social Sciences (KTS),
GESIS – Leibniz Institute for the Social Sciences, Cologne, Germany

Registration

Use the JCDL 2026 registration system: https://2026.jcdl.org/registration

Venue and Participation

The workshop is fully online via zoom and further details will be shared separately via email.

Code of Conduct

SESAME 2026 will follow the code of conduct as per JCDL guidelines.

Previous Editions

Contact

Questions? Email asif.suryani@gesis.org or open an issue in the SESAME GitHub repository.

Website Visitors: SESAME website visitor count

© 2026 SESAME Organizers • Previous Edition • Contact • GitHub Repository

Back to top ↑