CiteX 2026: Workshop on Citation Extraction and Parsing

Open and accurate citation data are a key component of transparent, reproducible and interconnected research. The Workshop on Citation Extraction and Parsing (CiteX 2026) provides an interdisciplinary forum for researchers, developers and practitioners to discuss current advances in the automated detection, structuring and provision of bibliographic references.

Building on initiatives such as WikiCite, WOOC, and the Frankfurt workshop series New Approaches for Extracting Heterogeneous Reference Data, CiteX 2026 aims to promote exchange between different professional communities working on methodological and infrastructural issues related to citation data. The workshop invites contributions on a wide range of topics – from rule-based and machine learning methods to the use of large language models (LLMs) for citation tasks.

Topics

• Automated extraction and parsing of references
• Creation and sharing of gold standards and test datasets
• Standardisation 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

Participation

Participation is possible with or without your own contribution. In-person participation is preferred, but a limited number of online contributions are also possible. A small fee will be charged to cover organisational costs.

Registration
Further information
Contact: d29ya3Nob3AuY2VwLjIwMjZAZ21haWwuY29t
OFFZIB project site