2nd LLMs4Subjects Shared Task: LLM-based Subject Tagging for Technical Library’s Digital Catalog
Participate in the 2nd LLMs4Subjects Shared Task, developing LLM-based solutions for subject tagging of technical records, with a focus on efficiency and bilingual language modeling.
The 2nd LLMs4Subjects Shared Task is now open for participation. This task challenges the research community to develop cutting-edge LLM-based solutions for subject tagging of technical records from Leibniz University’s Technical Library (TIBKAT).
Participants will leverage large language models (LLMs) to tag technical records using the GND taxonomy, with a focus on bilingual language modeling in German and English.
The task highlights the importance of efficiency in LLMs, encouraging participants to explore strategies that enhance model performance while optimizing for energy consumption and inference speed.
- Subtask 1: Multi-Domain Classification of Library Records
- Subtask 2: Large-scale Multilabel Subject Indexing of Library Records
Important dates:
- Release of training data: March 8, 2025
- Release of testing data: May 23, 2025
- Deadline for system submissions: June 2, 2025
- Evaluation end: June 27, 2025
- Paper submission deadline: July 7, 2025
- Notification of acceptance: June 28, 2025
- Camera-ready paper due: August 15, 2025
- Workshop/KONVENS: September 10 – 12, 2025 (TBA)
Learn more about the task and register now: 2nd LLMs4Subjects Shared Task | KONVENS 2025
Tags: LLMs4Subjects, Shared Task, LLM-based Subject Tagging, Technical Library, Digital Catalog, GND Taxonomy, Bilingual Language Modeling, Energy-Efficient LLMs, Compute-Efficient LLMs