# Cross-Modal Consistency in Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2411.09273 · HTML: https://mlsanity.com/paper/2411.09273/

## Key facts

- Cited by 19 papers in the map (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 19 of its 22 references that are in the map.
- First posted on arXiv 14 Nov 2024.

## 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, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning](https://mlsanity.com/paper/2311.10774/) (2023)
- [PromptCap: Prompt-Guided Task-Aware Image Captioning](https://mlsanity.com/paper/2211.09699/) (2022)
- [Don't Trust ChatGPT when Your Question is not in English: A Study of Multilingual Abilities and Types of LLMs](https://mlsanity.com/paper/2305.16339/) (2023)
- [On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving](https://mlsanity.com/paper/2311.05332/) (2023)
- [Can GPT-4V(ision) Serve Medical Applications? Case Studies on GPT-4V for Multimodal Medical Diagnosis](https://mlsanity.com/paper/2310.09909/) (2023)
- [LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning](https://mlsanity.com/paper/2007.08124/) (2020)
- [REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering](https://mlsanity.com/paper/2206.01201/) (2022)
- [Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond](https://mlsanity.com/paper/2310.02071/) (2023)
- [Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation](https://mlsanity.com/paper/2310.16809/) (2023)
- [Holistic Evaluation of GPT-4V for Biomedical Imaging](https://mlsanity.com/paper/2312.05256/) (2023)
- [TTIDA: Controllable Generative Data Augmentation via Text-to-Text and Text-to-Image Models](https://mlsanity.com/paper/2304.08821/) (2023)
- [MM-R3: On (In-)Consistency of Vision-Language Models (VLMs)](https://mlsanity.com/paper/2410.04778/) (2024)

## Built on by (most cited first, 19 of 19)

- [TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysis](https://mlsanity.com/paper/2510.01538/) (2025)
- [Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?](https://mlsanity.com/paper/2501.02669/) (2025)
- [PosterGen: Aesthetic-Aware Multi-Modal Paper-to-Poster Generation via Multi-Agent LLMs](https://mlsanity.com/paper/2508.17188/) (2025)
- [MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering](https://mlsanity.com/paper/2510.04217/) (2025)
- [See the Text: From Tokenization to Visual Reading](https://mlsanity.com/paper/2510.18840/) (2025)
- [Exploring and Evaluating Multimodal Knowledge Reasoning Consistency of Multimodal Large Language Models](https://mlsanity.com/paper/2503.04801/) (2025)
- [Same Content, Different Answers: Cross-Modal Inconsistency in MLLMs](https://mlsanity.com/paper/2512.08923/) (2025)
- [SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models](https://mlsanity.com/paper/2508.18179/) (2025)
- [XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models](https://mlsanity.com/paper/2510.15148/) (2025)
- [Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization](https://mlsanity.com/paper/2504.14858/) (2025)
- [Branch, or Layer? Zeroth-Order Optimization for Continual Learning of Vision-Language Models](https://mlsanity.com/paper/2506.12409/) (2025)
- [BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation](https://mlsanity.com/paper/2603.02816/) (2026)
- [VL-MedGuide: A Visual-Linguistic Large Model for Intelligent and Explainable Skin Disease Auxiliary Diagnosis](https://mlsanity.com/paper/2508.06624/) (2025)
- [Information-Theoretic Decomposition for Multimodal Interaction Learning](https://mlsanity.com/paper/2606.11614/) (2026)
- [TokenSwap: Benchmarking and Reducing the Modality Gap in Multimodal LLMs](https://mlsanity.com/paper/2607.28640/) (2026)
- [Seeing Red, Thinking Bad: Color Bias in Vision Language Models](https://mlsanity.com/paper/2608.14286/) (2026)
- [Where a New Concept Must Enter: Entry Point Gates Cross-Task Usability in Unified Multimodal Models](https://mlsanity.com/paper/2608.17564/) (2026)
- [Not Another Text Benchmark: Putting the "Visual" Back in Visual Question Answering for Large Video Models](https://mlsanity.com/paper/2609.17112/) (2026)
- [What Comes Next? Omni-StoryBench for Evaluating Story-Grounded Omnimodal Generation](https://mlsanity.com/paper/2609.37317/) (2026)

## Abstract (arXiv)

Recent developments in multimodal methodologies have marked the beginning of an exciting era for models adept at processing diverse data types, encompassing text, audio, and visual content. Models like GPT-4V, which merge computer vision with advanced language processing, exhibit extraordinary proficiency in handling intricate tasks that require a simultaneous understanding of both textual and visual information. Prior research efforts have meticulously evaluated the efficacy of these Vision Large Language Models (VLLMs) in various domains, including object detection, image captioning, and other related fields. However, existing analyses have often suffered from limitations, primarily centering on the isolated evaluation of each modality's performance while neglecting to explore their intricate cross-modal interactions. Specifically, the question of whether these models achieve the same level of accuracy when confronted with identical task instances across different modalities remains unanswered. In this study, we take the initiative to delve into the interaction and comparison among these modalities of interest by introducing a novel concept termed cross-modal consistency. Furthermore, we propose a quantitative evaluation framework founded on this concept. Our experimental findings, drawn from a curated collection of parallel vision-language datasets developed by us, unveil a pronounced inconsistency between the vision and language modalities within GPT-4V, despite its portrayal as a unified multimodal model. Our research yields insights into the appropriate utilization of such models and hints at potential avenues for enhancing their design.