Citation Extraction and Parsing 

About the Workshop

Accurate and open citation data are essential foundations for transparent, reproducible, and networked scholarship. The Workshop on Citation Extraction and Parsing (CiteX 2026) provides an interdisciplinary forum for researchers, developers, and practitioners to explore current advances in the automated identification, structuring, and dissemination of bibliographic references.

Building upon the growing momentum around open citations and initiatives such as WikiCite, WOOC, and the Frankfurt Workshop series, CiteX 2026 aims to foster dialogue across communities working on both the methodological and infrastructural aspects of citation data. The workshop welcomes contributions addressing technical innovations—ranging from traditional rule-based and machine-learning methods to state-of-the-art approaches using large language models (LLMs)—as well as practical and conceptual discussions about the creation, quality, and integration of open citation datasets.

CiteX 2026 invites participation from all disciplines interested in the extraction, parsing, and reuse of citation information. By bringing together perspectives from research, infrastructure, and applied contexts, the workshop seeks to strengthen collaboration, identify shared challenges, and promote the development of interoperable and openly accessible citation ecosystems.

Registration

Registration is now open! Registrate via https://t1p.de/p6e0s.

Workshop contributions: Titles & Authors

• Title: “Reference extraction in the bibliometric hinterlands - recovering from domain switch with GROBID”

  • Authors: Paul Donner; Yi Wen

• Title: “References Tractor: Citation Extraction and Linking with API-Retrieval from Scholarly Knowledge Graphs”

  • Authors: Nicolau Duran-Silva; Pablo Accuosto; Nicandro Bovenzi

• Title: “Detecting and classifying publications based on their abstracts with LLM embeddings and multi-label classifiers”

  • Authors: Annika Buchholz; Imene Khebouri; Thorsten Koch; Wolfgang Peters-Kottig; Tim Kunt; Tomasz Stompor; Thi Huong Vu; Janina Zittel

• Title: “An Iterative OCR and LLM-Based Workflow for High-Accuracy Citation Extraction in Large-Scale Bibliographic Corpora”

  • Authors: Abdallah Mohamed Abdallah Abdelnaby; Zeki Mustafa Doğan; Jörg-Holger Panzer; Lilja Mareike Sautter

• Title: “Open Social Science Citation Index (OpenSSCI). A Dataset of Metadata and Citation Links from SSOAR produced by the OUTCITE Project”

  • Authors: Muhammad Ahsan Shahid; Philipp Mayr

• Title: “RenoBench: A citation parsing benchmark”

  • Authors: Parth Sarin; Juan Pablo Alperin; Dione Mentis; Adam Buttrick

• Title: “Why citation processing remains challenging in SSH publications: toward a robust and scalable GRAPHIA Citation Index API”

  • Authors: Matteo Romanello; Yurui Zhu; Noushin Najafiragheb; Patryk Hubar-Kołodziejczyk; Marta Soricetti; Angelo Di Iorio; Julien Homo

• Title: “Identifying Citation Elements from Footnotes in Monographs Using Computer Vision and Natural Language Processing Methods”

  • Authors: Michal Ulaniuk; Przemys law Korytkowski

• Title: “Bibliographical Parsing of Descriptive Linguistic Literature”

  • Authors: Harald Hammarström

• Title: “CEC: A Tool for Context-Aware Citation Extraction and Citation Intent Classification from Scholarly PDFs”

  • Authors: Angelo Di Iorio; Ivan Heibi; Silvio Peroni; Lorenzo Paolini; Marta Soricetti

• Title: “Extraction of citation metadata in law and the humanities using Grobid: a new workflow, dataset, and model”

  • Authors: Luca Foppiano; Christian Boulanger

• Title: “Stackable Citation Knowledge: Building on Nanopublications for Climate and Biodiversity Research”

  • Authors: Anne Fouilloux; Jean Iaquinta

• Title: “LLM supported annotation and reference style recognition – pilot study with educational research publications”

  • Authors: Muhammad Ahsan Shahid; Ezgi Tugyan; Anele Schmidt; Verena Weimer; Tamara Heck; Philipp Mayr; Christoph Schindler; Thomas Oerder

Tentative Program (The detailed program will be finalized and published shortly) 

28.-29. May 2026

14 Contributions. Each 20 min. speech time.

DAY 1

12:00-1:00 pm Arrival

1:00-1:30 pm Ignition Talk (30 Min)

1:30-2:30 pm 2 Presentations

2:30-3:00 pm Break

3:00-4:00 pm 2 Presentations

4:00-4:15 pm Break

4:15-5:45 pm 3 Presentations

DAY 2

9:00-10:00 am Wrap-Up Workshop

10:00-11:00 am 2 Presentations

11:00-11:15 am Break

11:15-12:45 pm 3 Presentations

12:45-1:30 pm Lunch

1:30-2:30 pm 2 Presentations

2:30-3:00 pm Ignition Talk

3:00-3:30 pm End discussion and Good bye 

Topics

• Automated extraction and parsing of references

• Creation and sharing of gold standards and test datasets

• Standardization and interoperability of citation data

• Quality assessment and validation of extracted references

• Provision and integration of open citation data into repositories and search systems

• Citation practices across disciplines

• Data linking between scholarly works, datasets, and other research outputs

• Annotation and enrichment of citation data

• Prompt engineering and fine-tuning of LLMs (e.g., GPT-4, LLaMA) for citation tasks

• Comparison of LLM-based and tool-based (e.g., GROBID, Anystyle, Cermine) extraction pipelines

• In-text citation extraction and context analysis using LLMs

• Use of open web search APIs or LLMs for source retrieval

Contributions, Participation and Participation fees

We are looking forward to receiving submissions for presentations, poster and hands-on sessions.

We do prefer presenters to participate on-site; however we try to make oral presentations possible. Please indicate if you will attend on-site or online in the submissions form.

Participation is as well possible without contribution. We will charge 36 Euro for on-site-participation to cover the costs for organisation. Online participation is free of charge. 

Submission guidelines

• Please submit an extended abstract (1250-1500 words excl. references) for any contribution format.

• Only submissions in English will be considered.

• Accepted extended abstract will be published under a Zenodo community.

• Please indicate in the submission form, if you are interested in a Special Issue.

Important Dates

• Submission deadline:   01. February 2026

• Camera-ready version: 31.03.2026

• Workshop dates: 28./ 29. May 2026

Venue

• The Workshop will take place at DIPF | Leibniz Institute of Research and Information in Education, Rostocker Straße 6, 60323 Frankfurt a. M.

Submission &  Contact

Programme Committee