AlignBench：基于合成图文对的细粒度图文对齐基准评测

摘要

评估CLIP等图文对齐模型对于 bridging 视觉与语言表征至关重要。然而现有基准依赖基于规则的扰动或简短描述，限制了其衡量细粒度对齐的能力。我们推出AlignBench基准，通过评估多种图生文与文生图模型生成的精细图文配对，为图文对齐提供了全新衡量指标。每个句子均标注正确性，可直接评估视觉语言模型作为对齐评判器的能力。对大量基于解码器的视觉语言模型进行基准测试后，我们获得三项关键发现：(i) 基于CLIP的模型（即便是专为组合推理优化的版本）仍近乎"失明"；(ii) 检测器系统性地高估前序句子的得分；(iii) 它们表现出强烈的自我偏好，倾向于给自身输出更高评分，从而损害检测性能。项目页面详见https://dahlian00.github.io/AlignBench/。

English

Assessing image-text alignment models such as CLIP is crucial for bridging visual and linguistic representations. Yet existing benchmarks rely on rule-based perturbations or short captions, limiting their ability to measure fine-grained alignment. We introduce AlignBench, a benchmark that provides a new indicator of image-text alignment by evaluating detailed image-caption pairs generated by diverse image-to-text and text-to-image models. Each sentence is annotated for correctness, enabling direct assessment of VLMs as alignment evaluators. Benchmarking a wide range of decoder-based VLMs reveals three key findings: (i) CLIP-based models, even those tailored for compositional reasoning, remain nearly blind; (ii) detectors systematically over-score early sentences; and (iii) they show strong self-preference, favoring their own outputs and harming detection performance. Our project page will be available at https://dahlian00.github.io/AlignBench/.

AlignBench：基于合成图文对的细粒度图文对齐基准评测

AlignBench: Benchmarking Fine-Grained Image-Text Alignment with Synthetic Image-Caption Pairs

摘要

Support