# Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment

arXiv: https://arxiv.org/abs/2411.17188 · HTML: https://mlsanity.com/paper/2411.17188/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2024.

## Built on by (most cited first, 21 of 21)

- [Emu3.5: Native Multimodal Models are World Learners](https://mlsanity.com/paper/2510.26583/) (2025)
- [Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities](https://mlsanity.com/paper/2505.02567/) (2025)
- [Large Language Models for Planning: A Comprehensive and Systematic Survey](https://mlsanity.com/paper/2505.19683/) (2025)
- [Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark](https://mlsanity.com/paper/2510.13759/) (2025)
- [Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image](https://mlsanity.com/paper/2512.16899/) (2025)
- [LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model](https://mlsanity.com/paper/2604.20796/) (2026)
- [Quantifying the Gap between Understanding and Generation within Unified Multimodal Models](https://mlsanity.com/paper/2602.02140/) (2026)
- [UEval: A Benchmark for Unified Multimodal Generation](https://mlsanity.com/paper/2601.22155/) (2026)
- [UniM: A Unified Any-to-Any Interleaved Multimodal Benchmark](https://mlsanity.com/paper/2603.05075/) (2026)
- [CODESYNC: Synchronizing Large Language Models with Dynamic Code Evolution at Scale](https://mlsanity.com/paper/2502.16645/) (2025)
- [MMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation](https://mlsanity.com/paper/2505.17613/) (2025)
- [M2IO-R1: An Efficient RL-Enhanced Reasoning Framework for Multimodal Retrieval Augmented Multimodal Generation](https://mlsanity.com/paper/2508.06328/) (2025)
- [LLM-I: LLMs are Naturally Interleaved Multimodal Creators](https://mlsanity.com/paper/2509.13642/) (2025)
- [Wan-Weaver: Interleaved Multi-modal Generation via Decoupled Training](https://mlsanity.com/paper/2603.25706/) (2026)
- [CountLoop: Training-Free High-Instance Image Generation via Iterative Agent Guidance](https://mlsanity.com/paper/2508.16644/) (2025)
- [A High-Quality Dataset and Reliable Evaluation for Interleaved Image-Text Generation](https://mlsanity.com/paper/2506.09427/) (2025)
- [Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation](https://mlsanity.com/paper/2605.29861/) (2026)
- [Pareto LoRA: Mitigating Modality Imbalance in Unified Multimodal Models via Pareto-Optimal Gradient Integration](https://mlsanity.com/paper/2606.17296/) (2026)
- [Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation](https://mlsanity.com/paper/2606.30054/) (2026)
- [ATP-Bench: Towards Agentic Tool Planning for MLLM Interleaved Generation](https://mlsanity.com/paper/2603.29902/) (2026)
- [IMUG-Bench: Benchmarking Unified Multimodal Models on Interleaved Understanding and Generation](https://mlsanity.com/paper/2606.09169/) (2026)

## Abstract (arXiv)

Many real-world user queries (e.g. "How do to make egg fried rice?") could benefit from systems capable of generating responses with both textual steps with accompanying images, similar to a cookbook. Models designed to generate interleaved text and images face challenges in ensuring consistency within and across these modalities. To address these challenges, we present ISG, a comprehensive evaluation framework for interleaved text-and-image generation. ISG leverages a scene graph structure to capture relationships between text and image blocks, evaluating responses on four levels of granularity: holistic, structural, block-level, and image-specific. This multi-tiered evaluation allows for a nuanced assessment of consistency, coherence, and accuracy, and provides interpretable question-answer feedback. In conjunction with ISG, we introduce a benchmark, ISG-Bench, encompassing 1,150 samples across 8 categories and 21 subcategories. This benchmark dataset includes complex language-vision dependencies and golden answers to evaluate models effectively on vision-centric tasks such as style transfer, a challenging area for current models. Using ISG-Bench, we demonstrate that recent unified vision-language models perform poorly on generating interleaved content. While compositional approaches that combine separate language and image models show a 111% improvement over unified models at the holistic level, their performance remains suboptimal at both block and image levels. To facilitate future work, we develop ISG-Agent, a baseline agent employing a "plan-execute-refine" pipeline to invoke tools, achieving a 122% performance improvement.