Re-Thinking the Automatic Evaluation of Image-Text Alignment in Text-to-Image Models

ACL ARR 2025 May Submission1458 Authors

Abstract: Text-to-image models often struggle to generate images that precisely match textual prompts. Prior research has extensively studied the evaluation of image-text alignment in text-to-image generation. However, existing evaluations primarily focus on agreement with human assessments, neglecting other critical properties of a trustworthy evaluation framework. In this work, we first identify two key aspects that a reliable evaluation should address. We then empirically demonstrate that current mainstream evaluation frameworks fail to fully satisfy these properties across a diverse range of metrics and models. We propose recommendations for improving image-text alignment evaluation.

Paper Type: Short

Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond

Research Area Keywords: cross-modal content generation, multimodality

Contribution Types: Model analysis & interpretability, Data analysis

Languages Studied: English

Keywords: cross-modal content generation, multimodality

Submission Number: 1458