2.1Basic
Users submit a receipt image and a question.
Read text, layout, and amounts together.
Choose two considerations.
× Incorrect
Verify multimodal capability and limits, and test OCR, resolution, table reading, and sensitive data with an appropriate evaluation set.
Detailed explanation
IncorrectImages remove the need for evidence or privacy controls
Additional modalities still need explanation and safety.
CorrectTest OCR errors, resolution, tables, and personal data
Image-specific quality and safety are measured.
IncorrectPass an image unchanged to a text-only model
The input modality is unsupported.
CorrectVerify a model's image and text capabilities and limitations
The model matches the input modalities.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 2.1のマルチモーダル基盤モデルと評価を確認する。
Official references
What to confirm
入力モダリティとモデル能力、画像特有の評価観点を説明できる。
Key points
- Multimodal
- OCR
- Image quality
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Compare the definition with the AIF-C01 objective and the service documentation before applying it.
- Keep the concept separate from a particular answer choice or implementation step.
Foundation review
Multimodal model
A model that accepts or produces more than one modality, such as text and images.
OCR
Optical character recognition that converts text visible in an image into machine-readable text.
Question IDAWS-AIF-227
EnvironmentAWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
Last technical review2026-08-20
Report an error or rights issue