# Editor's Choice: Evaluating Abstract Intent in Image Editing through Atomic Entity Analysis

arXiv: https://arxiv.org/abs/2605.14842 · HTML: https://mlsanity.com/paper/2605.14842/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 71 references that are in the map.
- First posted on arXiv 14 May 2026.

## Builds on (most cited first, 28 of 28)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Step1X-Edit: A Practical Framework for General Image Editing](https://mlsanity.com/paper/2504.17761/) (2025)
- [The Vendi Score: A Diversity Evaluation Metric for Machine Learning](https://mlsanity.com/paper/2210.02410/) (2022)
- [FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios](https://mlsanity.com/paper/2307.13528/) (2023)
- [Guiding Instruction-based Image Editing via Multimodal Large Language Models](https://mlsanity.com/paper/2309.17102/) (2023)
- [HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer](https://mlsanity.com/paper/2505.22705/) (2025)
- [GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing](https://mlsanity.com/paper/2503.10639/) (2025)
- [TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models](https://mlsanity.com/paper/2305.11171/) (2023)
- [GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset](https://mlsanity.com/paper/2507.21033/) (2025)
- [Visual Style Prompting with Swapping Self-Attention](https://mlsanity.com/paper/2402.12974/) (2024)
- [Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing](https://mlsanity.com/paper/2510.19808/) (2025)
- [Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models](https://mlsanity.com/paper/2411.07232/) (2024)
- [textttComplex-Edit: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmark](https://mlsanity.com/paper/2504.13143/) (2025)
- [EditThinker: Unlocking Iterative Reasoning for Any Image Editor](https://mlsanity.com/paper/2512.05965/) (2025)
- [GIE-Bench: Towards Grounded Evaluation for Text-Guided Image Editing](https://mlsanity.com/paper/2505.11493/) (2025)
- [CompBench: Benchmarking Complex Instruction-guided Image Editing](https://mlsanity.com/paper/2505.12200/) (2025)
- [PICABench: How Far Are We from Physically Realistic Image Editing?](https://mlsanity.com/paper/2510.17681/) (2025)
- [Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning](https://mlsanity.com/paper/2507.01908/) (2025)
- [Beyond Simple Edits: X-Planner for Complex Instruction-Based Image Editing](https://mlsanity.com/paper/2507.05259/) (2025)
- [TRUE: Re-evaluating Factual Consistency Evaluation](https://mlsanity.com/paper/2204.04991/) (2022)
- [FlexEdit: Marrying Free-Shape Masks to VLLM for Flexible Image Editing](https://mlsanity.com/paper/2408.12429/) (2024)
- [PhotoAgent: Exploratory Visual Aesthetic Planning with Large Vision Models](https://mlsanity.com/paper/2602.22809/) (2026)
- [Specify and Edit: Overcoming Ambiguity in Text-Based Image Editing](https://mlsanity.com/paper/2407.20232/) (2024)
- [Re-Thinking the Automatic Evaluation of Image-Text Alignment in Text-to-Image Models](https://mlsanity.com/paper/2506.08480/) (2025)

## Abstract (arXiv)

Humans naturally communicate through abstract concepts like "mood". However, current image editing benchmarks focus primarily on explicit, literal commands, leaving abstract instructions largely underexplored. In this work, we first formalize the definition and taxonomy of abstract image editing. To measure instruction-following in this challenging domain, we introduce Entity-Rubrics, a framework that breaks down abstract edits into individual, entity-level assessments and achieves strong correlation with human judgment. Alongside this framework, we contribute AbstractEdit, the first benchmark dedicated to abstract image editing across diverse real-world scenes. Evaluating 11 leading models on this dataset reveals a fundamental challenge: standard architectures struggle to balance intent and preservation, commonly defaulting to under-editing or over-editing. Our analysis demonstrates that driving meaningful improvements relies heavily on integrating advanced LLM text encoders and iterative thinking. Looking forward, our entity-based paradigm can generalize beyond assessment to serve as a reward model, enable models to correctly interpret abstract communication, or highlight specific failures in test-time critique loops. Ultimately, we hope this work serves as a stepping stone toward seamless multimodal interaction, closing the gap between rigid machine execution and the natural, open-ended way humans communicate.