VisRAG-Ret-Test-ArxivQA: Visual Question Answering Dataset from arXiv Figures

A dataset for visual question answering based on figures extracted from arXiv publications. It originates from the ArXiVQA dataset within the Multimodal ArXiv collection. The dataset was created by openbmb and was last updated on March 15, 2025.

Use Cases

• Benchmarking visual question answering models based on academic figure content.
• Training multimodal retrieval systems for scientific document understanding.
• Evaluating the performance of retrieval-augmented generation (RAG) pipelines on technical imagery.

Strengths

• Based on a known source, the Multimodal ArXiv collection.
• Specifically designed for testing retrieval-augmented generation (RAG) systems.
• Last updated on March 15, 2025, indicating recent maintenance.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and license information are unknown, which may limit suitability assessment.

Provenance

Source

Figures extracted from arXiv publications via the ArXiVQA dataset.

Collection Method

Likely involves automated extraction and annotation of figures and associated questions from arXiv papers.

Time Range

null

Freshness

Last updated 2025-03-15 17:31:12.

Geography

null