REVEALER: Reinforcement-Guided Visual Reasoning for Element-Level Text-Image Alignment Evaluation

TL;DR

REVEALER introduces a reinforcement-guided visual reasoning framework for fine-grained, element-level evaluation of text-image alignment, improving interpretability and accuracy over existing methods.

Contribution

It presents a novel unified framework using reinforcement learning and structured reasoning for detailed alignment evaluation in text-to-image models.

Findings

Achieves state-of-the-art performance on four benchmarks.

Outperforms proprietary models and supervised baselines.

Demonstrates superior inference efficiency.

Abstract

Evaluating the alignment between textual prompts and generated images is critical for ensuring the reliability and usability of text-to-image (T2I) models. However, most existing evaluation methods rely on coarse-grained metrics or static QA pipelines, which lack fine-grained interpretability and struggle to reflect human preferences. To address this, we propose REVEALER, a unified framework for element-level alignment evaluation based on reinforcement-guided visual reasoning. Adopting a structured "grounding-reasoning-conclusion" paradigm, our method enables Multimodal Large Language Models (MLLMs) to explicitly localize semantic elements and derive interpretable alignment judgments. We optimize the model via Group Relative Policy Optimization(GRPO) using a composite reward function that incorporates structural format, grounding accuracy, and alignment fidelity. Extensive experiments across four benchmarks-EvalMuse-40K, RichHF, MHaluBench, and GenAI-Bench-demonstrate that REVEALER achieves state-of-the-art performance. Our approach consistently outperforms both strong proprietary models and supervised baselines while demonstrating superior inference efficiency compared to existing iterative visual reasoning methods.