KG20C & KG20C-QA: Scholarly Knowledge Graph Benchmarks
Research Paper#Knowledge Graphs, Question Answering, Scholarly Data🔬 Research|Analyzed: Jan 4, 2026 00:04•
Published: Dec 25, 2025 22:29
•1 min read
•ArXivAnalysis
This paper introduces KG20C and KG20C-QA, curated datasets for question answering (QA) research on scholarly data. It addresses the need for standardized benchmarks in this domain, providing a resource for both graph-based and text-based models. The paper's contribution lies in the formal documentation and release of these datasets, enabling reproducible research and facilitating advancements in QA and knowledge-driven applications within the scholarly domain.
Key Takeaways
- •Introduces KG20C and KG20C-QA, curated datasets for scholarly QA.
- •Provides formal documentation and release of the datasets.
- •Enables reproducible research and advancements in QA.
- •Supports both graph-based and text-based models.
Reference / Citation
View Original"By officially releasing these datasets with thorough documentation, we aim to contribute a reusable, extensible resource for the research community, enabling future work in QA, reasoning, and knowledge-driven applications in the scholarly domain."