Wiki-CoE: Multimodal Question Answering with Wikipedia Screenshots

Wiki-CoE is a multimodal question-answering dataset for evaluating visual reasoning and evidence localization. Each example pairs a natural-language question with one or more Wikipedia page screenshots, asking models to return both an answer and an explicit chain of supporting evidence. The dataset was created by PeiyangLiu and was last updated on the Hugging Face platform in May 2026.

Use Cases

• Evaluating visual reasoning capabilities based on Wikipedia screenshots.
• Training models for evidence localization within visual page content.
• Benchmarking chain-of-evidence generation in multimodal question answering.

Strengths

• Designed for explicit chain-of-evidence generation, a specific evaluation task.
• Pairs natural-language questions with visual evidence from Wikipedia screenshots.

Limitations

• Dataset size, row count, and column-level documentation are unknown.
• Last updated 2026-05-06 02:41:33; freshness should be verified.

Provenance

Source

Hugging Face dataset created by PeiyangLiu.

Collection Method

Likely constructed by pairing questions with screenshots of Wikipedia pages.

Freshness

Last updated 2026-05-06 02:41:33.