An Online Reference-Free Evaluation Framework for Flowchart Image-to-Code Generation
This addresses the challenge of continuous quality monitoring for flowchart processing systems in production, though it is incremental as it builds on existing vision-language models and evaluation techniques.
The paper tackles the problem of evaluating flowchart image-to-code generation in production where ground-truth code is unavailable, by proposing a reference-free framework with automated metrics that show strong agreement with ground-truth metrics (e.g., average Pearson's r = 0.94 for F1).
Vision-Language Models (VLMs) are increasingly used in document processing pipelines to convert flowchart images into structured code (e.g., Mermaid). In production, these systems process arbitrary inputs for which no ground-truth code exists, making output quality difficult to assess. We propose a reference-free evaluation framework that monitors flowchart image-to-code generation quality at inference time, using only the input image and the generated output. The framework introduces two automated metrics: $\text{Recall}{\text{OCR}}$, which estimates content coverage by extracting text from the input image via OCR as a proxy reference, and $\text{Precision}{\text{VE}}$, which detects hallucinated elements through Visual Entailment against the original image. Their harmonic mean, $\text{F1}{\text{OCR-VE}}$, provides a unified quality score. Validation on the FlowVQA dataset shows strong agreement with ground-truth metrics (average Pearson's $r = 0.97$, $0.91$, and $0.94$ for Recall, Precision, and F1, respectively), confirming the framework's reliability as a practical, reference-free alternative for continuous quality monitoring in production settings.