Multimodal-CoT

{
  "doc": "zhang-2023-multimodal.md",
  "context": "A two-stage framework that separates rationale generation and answer inference by incorporating vision and language modalities.",
  "category": "ai",
  "norm_label": "Multimodal-CoT",
  "graphify_id": "multimodal_cot_framework",
  "source_file": "zhang-2023-multimodal.md",
  "imported_from": "/Users/antonborzov/Documents/Research.nosync/papers/extract_typed_out/zhang-2023-multimodal/graph.json",
  "extracted_type": "framework",
  "source_location": "§4",
  "graphify_file_type": "framework"
}