IRCDL 2026
Information and Research Science Connecting to Digital and Library Science 2026

Table of Contents

• Preface
  Summary: There were 51 papers submitted for peer-review to this conference. Out of these, 38 papers were accepted for this volume, 24 as regular papers and 14 as short papers.

Track 1 - Computer Science Foundations for Digital Libraries: Algorithms, Systems, and Applications

• LLM-driven Open Information Extraction of Business Data from Documents on Climate Change
  Samuele Baroni, Chiara Ferri, Fabio Celli
• Semantic Digital Libraries in Public Administration: Optimizing Certificate Request Management
  Giovanni Carau, Pasquale D'Avino, Donatella Firmani, Elio Gullo, Luigi Laura
• A Quantitative Analysis of Diamond Open Access Publishing in Italy
  Simone Angioni, Miriam Baglioni, Alessia Bardi, Paolo Manghi, Andrea Mannocci, Gina Pavone
• AI in-the-loop: the AI-assisted digitisation workflow of the Fondazione Zeri’s auction catalogues collection
  Paolo Bonora, Tommaso Vitale
• Document Processing and Knowledge Management for Digital Libraries
  Stefano Ferilli, Eleonora Bernasconi, Domenico Redavid
• Improving large-scale DLA datasets through semantic validation and relation-aware multimodal LLMs
  Lorenzo Massai, Simone Marinai
• Harnessing Self-Supervised Features for Art Classification
  Federico Melis, Davide Bilardello, Emanuele Prato, Evelyn Turri, Lorenzo Baraldi
• An Open-Source solution for layout parsing of historical Italian newspapers
  Silvano Imboden, Antonella Guidazzoli, Donatella Sforzini, Luca Mattei, Gabriele Marconi, Federico Andrucci, Alex Gianelli, Simona Caraceni, Rossella Pansini, Gabriele Fatigati, Fauzia Albertin, Giovanni Baisi, Giorgia Cardano, Maria Chiara Liguori, Angela Lanzarini
• Querying LLMs as if they were Digital Libraries
  Mirco Cazzaro, Gianmaria Silvello
• Automatic Domain Classification of Tabular Datasets Using Large Language Models
  Elizaveta Gamper, Irina Deeva
• Towards Real-world Application of Timeline Summarization in a Local Media
  Hayata Shinjo, Israel Mendonça, Masayoshi Aritsugi
• CroQS: Cross-modal Query Suggestion for Text-to-Image Retrieval in Image Archives
  Giacomo Pacini, Nicola Messina, Nicola Tonellotto, Giuseppe Amato, Fabrizio Falchi
• Evaluating RAG approaches for Question Answering
  Maristella Agosti, Nicola D'Errico, Paolo Fantozzi, Donatella Firmani, Luigi Laura
• An AI-based system for medico-legal document analysis
  Matteo Marulli, Marco Bertini
• MAGDA: A Clustering-Based Retrieval-Augmented Generation System for Gender Gap Analysis in Digital Libraries
  Marta Santacroce, Riccardo Benassi, Michele Luca Contalbo, Matteo Paganelli, Sara Pederzoli, Maurizio Vincini, Francesco Guerra
• Enhancing Interoperability of SPARQL Endpoints: RESTful and OAI-PMH API for the DH-ATLAS Project
  Giorgia Rubin, Alessia Bardi, Riccardo Del Gratta, Angelo Mario Del Grosso
• Piscis in tabula: Turning Environmental Data into Actionable Reports
  Beatrice Portelli, Alex Falcon, Daniele Lizzio Bosco, Paolo Tomè, Marco Galeotti, Snježana Zrnčić, Giuseppe Serra
• MetaFAIR Ecosystem for SSH Digital Libraries: Dataset Packaging, Validation, and SPARQL Publication
  Emiliano Degl'Innocenti, Francesco Pinna, Alessia Spadi, Federica Spinelli
• Annotaterm: A Fragment-Based Approach for Annotating Discontinuous Named Entities and Terms
  Giorgio Maria Di Nunzio, Federica Vezzani
• How Surprising Is Historical Italian to Language Models? Tokenization Tax, Comprehension Tax, and a Simple Mitigation
  Mariia Levchenko
• Efficient and Reliable Estimation of Named Entity Linking Quality: A Case Study on GutBrainIE
  Marco Martinelli, Stefano Marchesin, Gianmaria Silvello
• CHAD ASK: Experimenting with a semi-automatic approach based on online surveys to formalise unstructured knowledge in Linked Data
  Sebastian Barzaghi, Arianna Moretti, Ivan Heibi, Silvio Peroni
• Defining A Workflow For Semantic Enhancement Of Cultural Heritage Metadata
  Arianna Moretti
• Diagnosing Structural Failures in LLM-Based Evidence Extraction for Meta-Analysis
  Zhiyin Tan, Jennifer D’Souza

Track 2 - Digital Humanities: The Science and Foundation of Modern Humanities Libraries

• Lamba: Mamba State Space Model Adapted to Latin Semantic Retrieval
  Elia Scapini, Federico Iezzi
• The Codes Talk: Automated Extraction and Normalization of ISBNs for Metadata Integration
  Sania Aftar, Riccardo Amerigo Vigliermo, Sonia Bergamaschi
• The Joys and Sorrows of Data Normalization: Working with Sources from the Franciscan Custody of the Holy Land, XVII-XVIII Centuries
  Antonio Iodice, Alessia De Benedictis
• Beyond Archives: Designing a Segmentation and ATR Workflow for Mid-Twentieth-Century Italian Typescripts in a Relational Digital Library
  Giulia Lembo
• Tracing the art market: a hybrid approach to digitise historical auction catalogues
  Marilena Daquino, Francesca Mambelli, Valentina Pasqual, Valentina Rossetti, Francesca Tomasi
• Digital Approaches to Handwritten Text Recognition in Complex Art-Historical Archives: Towards a Robust Text Model for the Giovanni Battista Cavalcaselle Manuscripts
  Jenny Palermo
• FAIR Training Materials for Disciplinary Research Infrastructures: Metadata, Vocabularies, and Selective Harvesting in the H2IOSC Ecosystem
  Daniele Melaccio, Giulia Pedonese, Francesca Frontini, Iulianna van der Lek, Thalassia Kontino
• Metadata Analysis of Sakha Artefacts in Europeana
  Saiyyna Vasileva, Daniel Zilio
• SICHELIA: Sicilian Intangible Cultural Heritage Exploration Leveraging Open Data
  Giulia Speranza, Raffaele Manna, Maria Pia Di Buono
• Addressing the problem of file formats obsolescence using AI: the methodology proposed by Emilia-Romagna Digital Archival Centre
  Stefano Allegrezza, Cristiano Casagni, Marianna Tascone
• The Cartoonists Meta-description Framework
  Valerio De Luce, Tiberio Uricchio
• Data Affordances in Digital Humanities Information Visualization Practices
  Giulia Renda, Marilena Daquino
• Archival Knowledge Graphs: Balancing Semantic Richness and Accessibility of Hierarchical Structures
  Remo Grillo, Lucia Giagnolini, Paolo Bonora
• From a FAIR Workflow Blueprint to an Executable Data Harmonisation Pipeline: Exploiting the BnF SPARQL Service to Produce and Disseminate an Early Modern Research-Oriented Bibliographic Dataset
  Arianna Moretti, Iiro L. I. Tiihonen, Jonas P. Fischer