First Workshop on Building Innovative Research Systems for Digital Libraries (BIRDS 2025)

2025-09-30

AI Summary

Digital libraries face escalating information overload, rendering generic large language models (e.g., ChatGPT) insufficient for domain-specific intelligent access. Method: This project proposes a synergistic design framework integrating information retrieval (IR), domain-adapted natural language processing (NLP), data modeling, and lightweight large language models. It pioneers a cross-disciplinary collaboration mechanism uniting digital library practitioners with IR/NLP researchers, validated through an international workshop to identify core challenges—semantic understanding in professional contexts, structured knowledge guidance, and interpretable retrieval. Contribution/Results: The project establishes foundational design principles and a prototype architecture for intelligent digital library access systems. It delivers a methodological framework and practical paradigm to bridge the gap between general-purpose LLM capabilities and the rigorous, context-sensitive requirements of vertical domains—thereby advancing domain-aware AI for scholarly infrastructure.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Application Domains: Humanities & Computational Social Science

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

We propose the first workshop on Building Innovative Research Systems for Digital Libraries (BIRDS) to take place at TPDL 2025 as a full-day workshop. BIRDS addresses practitioners working in digital libraries and GLAMs as well as researchers from computational domains such as data science, information retrieval, natural language processing, and data modelling. Our interdisciplinary workshop focuses on connecting members of both worlds. One of today's biggest challenges is the increasing information flood. Large language models like ChatGPT seem to offer good performance for answering questions on the web. So, shall we just build upon that idea and use chatbots in digital libraries? Or do we need to design and develop specialized and effective access paths? Answering these questions requires to connect different communities, practitioners from real digital libraries and researchers in the area of computer science. In brief, our workshop's goal is thus to support researchers and practitioners to build the next generation of innovative and effective digital library systems.

Problem

• Addressing information flood in digital libraries
• Exploring specialized access paths versus chatbots
• Connecting practitioners and researchers for innovation

Innovation

• Workshop connects digital library practitioners with computational researchers
• Explores specialized access paths beyond generic chatbot solutions
• Builds next-generation digital library systems through interdisciplinary collaboration