REVEALER: Reinforcement-Guided Visual Reasoning for Element-Level Text-Image Alignment Evaluation
Year: 2026
Type: conference-paper
Abstract: Evaluating the alignment between textual prompts and generated images is critical for ensuring the reliability and usability of textto-image (T2I) models.However, most existing evaluation methods rely on coarsegrained metrics or static Question Answering (QA) pipelines, which lack fine-grained interpretability and struggle to reflect human preferences.To address this, we propose REVEALER, a reinforcement-guided visual reasoning framework for element-level textto-image alignment evaluation.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 multi-dimensional reward function that targets format compliance, localization precision, and alignment accuracy.Extensive experiments confirm that RE-VEALER achieves state-of-the-art results across four benchmarks.Notably, on EvalMuse-40K, it surpasses the strong proprietary Gemini 3 Pro and Training-based baselines with absolute accuracy gains of +4.2% and +13.3%, respectively.Ablation studies further demonstrate the efficacy of our method, contributing a cumulative 19.6% improvement over the base model.
Authors: FuLin Shi, Wenyi Xiao, Leilei Gan, Liang Ding, Binchen
Institutions: Zhejiang University, Alibaba Group (China)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166824763