Research map / Vision-language and multimodal / Visual question answering
SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add arithmetic-expression generation instead of directly predicting numeric answers (ablation) | M3D · SlideVQA dev | JEM: 35.7 -> 36.2 | Helped |
| add arithmetic-expression generation instead of directly predicting numeric answers (ablation) | M3D · SlideVQA dev | QA EM: 40.5 -> 41.3 | Helped |
| add evidence selection (ablation) | M3D · SlideVQA dev | QA EM: 40.6 -> 41.3 | Helped |
| add layout features (ablation) | M3D · SlideVQA dev | JEM: 35.1 -> 36.2 | Helped |
| add visual features (ablation) | M3D · SlideVQA dev | JEM: 34.2 -> 36.2 | Helped |
| add text features (ablation) | M3D · SlideVQA dev | JEM: 1.0 -> 36.2 | Helped |
| use separate evidence-selection and QA generations rather than BinaryClass classification | M3D backbone · SlideVQA dev | Main JEM: 24.7 -> 35.7 | Helped |
| use separate evidence-selection and QA generations rather than one combined ChainGen sequence | M3D backbone · SlideVQA dev | Main JEM: 34.0 -> 35.7 | Helped |
| provide ground-truth evidence slides | M3D · SlideVQA test | JEM: 28.0 -> 35.4 | Helped |
Closest papers by meaning
- VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning (CVPR 2024 · similarity 0.91)
- GRAM: Global Reasoning for Multi-Page VQA (CVPR 2024 · similarity 0.90)
- Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering (NeurIPS 2025 · similarity 0.89)
- Separation of Powers: On Segregating Knowledge from Observation in LLM-enabled Knowledge-based Visual Question Answering (CVPR 2025 · similarity 0.88)
- Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding (CVPR 2025 · similarity 0.88)
- When Open-Vocabulary Visual Question Answering Meets Causal Adapter: Benchmark and Approach (AAAI 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.