Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Wenchao, Tian, Jiahe, He, Runze, Han, Jizhong, Dai, Jiao, Feng, Miaomiao, Mi, Wei, Zhang, Xiaodan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916756698693632
author Zhang, Wenchao
Tian, Jiahe
He, Runze
Han, Jizhong
Dai, Jiao
Feng, Miaomiao
Mi, Wei
Zhang, Xiaodan
author_facet Zhang, Wenchao
Tian, Jiahe
He, Runze
Han, Jizhong
Dai, Jiao
Feng, Miaomiao
Mi, Wei
Zhang, Xiaodan
contents Recent text-to-image (T2I) generation models have advanced significantly, enabling the creation of high-fidelity images from textual prompts. However, existing evaluation benchmarks primarily focus on the explicit alignment between generated images and prompts, neglecting the alignment with real-world knowledge beyond prompts. To address this gap, we introduce Align Beyond Prompts (ABP), a comprehensive benchmark designed to measure the alignment of generated images with real-world knowledge that extends beyond the explicit user prompts. ABP comprises over 2,000 meticulously crafted prompts, covering real-world knowledge across six distinct scenarios. We further introduce ABPScore, a metric that utilizes existing Multimodal Large Language Models (MLLMs) to assess the alignment between generated images and world knowledge beyond prompts, which demonstrates strong correlations with human judgments. Through a comprehensive evaluation of 8 popular T2I models using ABP, we find that even state-of-the-art models, such as GPT-4o, face limitations in integrating simple real-world knowledge into generated images. To mitigate this issue, we introduce a training-free strategy within ABP, named Inference-Time Knowledge Injection (ITKI). By applying this strategy to optimize 200 challenging samples, we achieved an improvement of approximately 43% in ABPScore. The dataset and code are available in https://github.com/smile365317/ABP.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18730
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image Generation
Zhang, Wenchao
Tian, Jiahe
He, Runze
Han, Jizhong
Dai, Jiao
Feng, Miaomiao
Mi, Wei
Zhang, Xiaodan
Computer Vision and Pattern Recognition
Recent text-to-image (T2I) generation models have advanced significantly, enabling the creation of high-fidelity images from textual prompts. However, existing evaluation benchmarks primarily focus on the explicit alignment between generated images and prompts, neglecting the alignment with real-world knowledge beyond prompts. To address this gap, we introduce Align Beyond Prompts (ABP), a comprehensive benchmark designed to measure the alignment of generated images with real-world knowledge that extends beyond the explicit user prompts. ABP comprises over 2,000 meticulously crafted prompts, covering real-world knowledge across six distinct scenarios. We further introduce ABPScore, a metric that utilizes existing Multimodal Large Language Models (MLLMs) to assess the alignment between generated images and world knowledge beyond prompts, which demonstrates strong correlations with human judgments. Through a comprehensive evaluation of 8 popular T2I models using ABP, we find that even state-of-the-art models, such as GPT-4o, face limitations in integrating simple real-world knowledge into generated images. To mitigate this issue, we introduce a training-free strategy within ABP, named Inference-Time Knowledge Injection (ITKI). By applying this strategy to optimize 200 challenging samples, we achieved an improvement of approximately 43% in ABPScore. The dataset and code are available in https://github.com/smile365317/ABP.
title Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.18730