| Homepage | http://ws.nju.edu.cn/~gcheng |
📌 Reminder: ISWC 2025 Posters & Demos Deadline – July 31!
Got a tool, prototype, or early-stage idea? Share it with the community at ISWC 2025!
🗓️ Deadline: July 31, 2025
🔗https://iswc2025.semanticweb.org/#/calls/posters
#ISWC2025 #Posters #Demos #SemanticWeb #KnowledgeGraphs #LLM #AI
The rapid growth of open source machine learning (ML) resources, such as models and datasets, has accelerated IR research. However, existing platforms like Hugging Face do not explicitly utilize structured representations, limiting advanced queries and analyses such as tracing model evolution and recommending relevant datasets. To fill the gap, we construct HuggingKG, the first large-scale knowledge graph built from the Hugging Face community for ML resource management. With 2.6 million nodes and 6.2 million edges, HuggingKG captures domain-specific relations and rich textual attributes. It enables us to further present HuggingBench, a multi-task benchmark with three novel test collections for IR tasks including resource recommendation, classification, and tracing. Our experiments reveal unique characteristics of HuggingKG and the derived tasks. Both resources are publicly available, expected to advance research in open source resource sharing and management.
Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for enhancing the capabilities of large language models. However, existing RAG evaluation predominantly focuses on text retrieval and relies on opaque, end-to-end assessments of generated outputs. To address these limitations, we introduce mmRAG, a modular benchmark designed for evaluating multi-modal RAG systems. Our benchmark integrates queries from six diverse question-answering datasets spanning text, tables, and knowledge graphs, which we uniformly convert into retrievable documents. To enable direct, granular evaluation of individual RAG components -- such as the accuracy of retrieval and query routing -- beyond end-to-end generation quality, we follow standard information retrieval procedures to annotate document relevance and derive dataset relevance. We establish baseline performance by evaluating a wide range of RAG implementations on mmRAG.
📢 Reminder for ISWC authors!
If you have submitted an abstract, don't forget to upload your paper by tomorrow - May 13th (Anywhere on Earth). ⏳
⏰ The clock is ticking! ⏰
This is your last chance to submit to the ISWC Research, Resource, and In-use Tracks!
🎉 Ever wondered how ISWC has grown over the years?
Find out in our new blog post: a data-powered tour through two decades of Semantic Web research 🕸️📚
🔗 https://iswc2025.semanticweb.org/#/blogs/naturenavigator
👏 Huge thanks to @angelosalatino for this fun and insightful piece!
🚀Discover Nara, Japan – The Host City of ISWC 2025! 🇯🇵
The ISWC Conference isn’t just about cutting-edge research – it's also a chance to explore an amazing city. This year, we are heading to Nara, Japan, a place where history, culture, and innovation come together.
📖 Blog post about Nara: https://iswc2025.semanticweb.org/#/blogs/host
Have you been to Nara before? Share your favorite spots below! 👇
🚀 Exciting News! The Deadline for Challenge Proposal Submission Has Been Extended! 🚀
We are giving you more time to submit your proposal – the new deadline is now March 4!
This is your opportunity to showcase innovative ideas, tackle real-world problems, and make a meaningful impact.
ISWC 2026