# MetaLogic: Robustness Evaluation of Text-to-Image Models via Logically Equivalent Prompts

arXiv: https://arxiv.org/abs/2510.00796 · HTML: https://mlsanity.com/paper/2510.00796/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 25 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Towards Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2212.10403/) (2022)
- [GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models](https://mlsanity.com/paper/2410.05229/) (2024)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks](https://mlsanity.com/paper/2311.06242/) (2023)
- [Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing](https://mlsanity.com/paper/2309.15664/) (2023)
- [Metamorphic Testing: A New Approach for Generating Next Test Cases](https://mlsanity.com/paper/2002.12543/) (2020)
- [Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?](https://mlsanity.com/paper/2406.07546/) (2024)
- [Dynamic Prompt Optimizing for Text-to-Image Generation](https://mlsanity.com/paper/2404.04095/) (2024)
- [Divide, Evaluate, and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA Feedback](https://mlsanity.com/paper/2307.04749/) (2023)
- [LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models](https://mlsanity.com/paper/2401.00757/) (2024)
- [TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation](https://mlsanity.com/paper/2307.05134/) (2023)
- [Predicated Diffusion: Predicate Logic-Based Attention Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2311.16117/) (2023)
- [An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics](https://mlsanity.com/paper/2305.14998/) (2023)
- [Relations, Negations, and Numbers: Looking for Logic in Generative Text-to-Image Models](https://mlsanity.com/paper/2411.17066/) (2024)

## Built on by (most cited first, 1 of 1)

- [Prototypicality Bias Reveals Blindspots in Multimodal Evaluation Metrics](https://mlsanity.com/paper/2601.04946/) (2026)

## Abstract (arXiv)

Recent advances in text-to-image (T2I) models, especially diffusion-based architectures, have significantly improved the visual quality of generated images. However, these models continue to struggle with a critical limitation: maintaining semantic consistency when input prompts undergo minor linguistic variations. Despite being logically equivalent, such prompt pairs often yield misaligned or semantically inconsistent images, exposing a lack of robustness in reasoning and generalisation. To address this, we propose MetaLogic, a novel evaluation framework that detects T2I misalignment without relying on ground truth images. MetaLogic leverages metamorphic testing, generating image pairs from prompts that differ grammatically but are semantically identical. By directly comparing these image pairs, the framework identifies inconsistencies that signal failures in preserving the intended meaning, effectively diagnosing robustness issues in the model's logic understanding. Unlike existing evaluation methods that compare a generated image to a single prompt, MetaLogic evaluates semantic equivalence between paired images, offering a scalable, ground-truth-free approach to identifying alignment failures. It categorises these alignment errors (e.g., entity omission, duplication, positional misalignment) and surfaces counterexamples that can be used for model debugging and refinement. We evaluate MetaLogic across multiple state-of-the-art T2I models and reveal consistent robustness failures across a range of logical constructs. We find that even the SOTA text-to-image models like Flux.dev and DALLE-3 demonstrate a 59 percent and 71 percent misalignment rate, respectively. Our results show that MetaLogic is not only efficient and scalable, but also effective in uncovering fine-grained logical inconsistencies that are overlooked by existing evaluation metrics.