A seven-stage OCR plus arrow-detection prompt pipeline lifts GPT-4o flowchart QA accuracy from 80% to 89% on 90 self-annotated questions, without task-specific fine-tuning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Arrow-Guided VLM: Enhancing Flowchart Understanding via Arrow Direction Encoding
A seven-stage OCR plus arrow-detection prompt pipeline lifts GPT-4o flowchart QA accuracy from 80% to 89% on 90 self-annotated questions, without task-specific fine-tuning.