# Measuring What Matters Beyond Text: Evaluating Multimodal Summaries by Quality, Alignment, and Diversity

arXiv: https://arxiv.org/abs/2605.11693 · HTML: https://mlsanity.com/paper/2605.11693/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 10 of its 31 references that are in the map.
- First posted on arXiv 12 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 10 of 10)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Measuring Diversity in Co-creative Image Generation](https://mlsanity.com/paper/2403.13826/) (2024)
- [Scendi Score: Prompt-Aware Diversity Evaluation via Schur Complement of CLIP Embeddings](https://mlsanity.com/paper/2412.18645/) (2024)
- [Exploiting Pseudo Image Captions for Multimodal Summarization](https://mlsanity.com/paper/2305.05496/) (2023)
- [Fine-grained and Explainable Factuality Evaluation for Multimodal Summarization](https://mlsanity.com/paper/2402.11414/) (2024)
- [Evaluate Summarization in Fine-Granularity: Auto Evaluation with LLM](https://mlsanity.com/paper/2412.19906/) (2024)
- [OpenFActScore: Open-Source Atomic Evaluation of Factuality in Text Generation](https://mlsanity.com/paper/2507.05965/) (2025)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) have facilitated Multimodal Summarization with Multimodal Output (MSMO), wherein systems generate concise textual summaries accompanied by salient visuals from multimodal sources. However, current MSMO evaluation remains fragmented: text quality, image-text alignment, and visual diversity are typically assessed in isolation using unimodal metrics, making it difficult to capture whether the modalities jointly support a faithful and useful summary. To address this gap, we introduce MM-Eval, a unified evaluation framework that integrates assessments of textual quality, cross-modal alignment, and visual diversity. MM-Eval comprises three components: (1) text quality, measured using OpenFActScore for factual consistency and G-Eval for coherence, fluency, and relevance; (2) image-text relevance, evaluated via an MLLM-as-a-judge approach; and (3) image-set diversity, quantified using Truncated CLIP Entropy. We calibrate MM-Eval through a learned aggregation model trained on the mLLM-EVAL news benchmark, aligning component contributions with human preferences. Our analysis reveals a text-dominant hierarchy in this setting, where factual consistency acts as a critical determinant of perceived overall quality, while visual relevance and diversity provide complementary signals. MM-Eval improves over heuristic aggregation baselines and provides an interpretable, reference-weak framework for comparative evaluation of multimodal summaries.